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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sudden or significant changes or events

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to critical situations or decline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hander
    -0.73
    ership
    -0.73
    erness
    -0.70
    Ĥ¬
    -0.70
    alam
    -0.68
    pocket
    -0.67
    rooms
    -0.66
    weekly
    -0.65
    wana
    -0.64
    verbs
    -0.63
    POSITIVE LOGITS
     precip
    1.57
    itous
    1.48
    itating
    1.00
    itant
    0.94
    itates
    0.93
    itated
    0.93
    itate
    0.91
    uating
    0.88
    itial
    0.87
    uations
    0.84
    Act Density 0.010%

    No Known Activations