Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to preventing or responding to negative events or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the continuation or prevention of an action or event.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    phrases related to prevention and justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orers
    -0.75
     monop
    -0.70
     multip
    -0.69
     extras
    -0.69
     surplus
    -0.68
    quartered
    -0.67
     pilgr
    -0.64
     regulars
    -0.63
     shuttle
    -0.61
    ortment
    -0.61
    POSITIVE LOGITS
     unchecked
    0.83
    .","
    0.77
    .</
    0.75
     happening
    0.74
     propag
    0.72
     happen
    0.72
     perpetrated
    0.70
     forever
    0.70
     reverber
    0.70
    rue
    0.69
    Act Density 0.432%

    No Known Activations