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

    Neuronpedia

    INDEX
    Explanations

    visual descriptions of how things appear

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating perception or appearance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kson
    -0.77
    wu
    -0.73
    âĹ¼
    -0.73
    verend
    -0.71
    venient
    -0.70
    essional
    -0.70
    iling
    -0.70
    learning
    -0.69
    umbn
    -0.69
    ricular
    -0.69
    POSITIVE LOGITS
     suspic
    0.76
    ahead
    0.71
    bones
    0.69
    ynt
    0.69
    ãĤ¶
    0.68
     shif
    0.68
     unbeat
    0.67
     noses
    0.64
     awfully
    0.64
     suspicious
    0.64
    Act Density 0.058%

    No Known Activations