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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "look" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss visual appearances or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Literature
    -0.70
    Staff
    -0.68
    actionDate
    -0.66
    EStreamFrame
    -0.66
     Kurd
    -0.64
    ommod
    -0.63
    cffff
    -0.63
     Loch
    -0.63
    CENT
    -0.62
    KEN
    -0.62
    POSITIVE LOGITS
    ahead
    1.07
    checks
    0.86
    finder
    0.82
    outs
    0.81
    lessly
    0.78
    ENE
    0.76
    ups
    0.76
    behind
    0.74
    anka
    0.73
    apeshifter
    0.72
    Act Density 0.025%

    No Known Activations