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

    Neuronpedia

    INDEX
    Explanations

    phrases instructing to pay attention to specific things or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to watching or monitoring something attentively

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venge
    -0.80
     Gibbs
    -0.66
     Guitar
    -0.65
    HAHAHAHA
    -0.63
    Grade
    -0.62
    bet
    -0.61
     Whites
    -0.61
    DNA
    -0.61
    hens
    -0.61
    ĪĴ
    -0.60
    POSITIVE LOGITS
    âĦ¢:
    0.74
     ahead
    0.73
    eful
    0.73
    gency
    0.71
    ulatory
    0.70
    emark
    0.70
    ãĤ¶
    0.67
    oin
    0.67
    agascar
    0.66
    uum
    0.66
    Act Density 0.031%

    No Known Activations