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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs indicating a negative outcome or conflict

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    00200000
    -0.64
    oka
    -0.63
    minist
    -0.62
    accompanied
    -0.61
    gel
    -0.61
    erala
    -0.60
    ikk
    -0.60
    itatively
    -0.60
    izing
    -0.60
    anza
    -0.59
    POSITIVE LOGITS
    neck
    1.19
    fast
    1.04
    down
    0.81
    away
    0.80
    downs
    0.76
     curfew
    0.76
     loose
    0.76
     necks
    0.76
    DOWN
    0.75
    waters
    0.74
    Act Density 0.640%

    No Known Activations