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

    Neuronpedia

    INDEX
    Explanations

    words related to description of appearance or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a superficial or first impression evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.66
    elsen
    -0.63
    icer
    -0.62
    artney
    -0.61
    cellaneous
    -0.60
    umbn
    -0.60
    rench
    -0.60
    die
    -0.60
    gypt
    -0.60
    rus
    -0.60
    POSITIVE LOGITS
     speaking
    0.86
     glance
    0.77
     it
    0.70
     terms
    0.65
     yes
    0.65
     anyway
    0.65
     this
    0.62
    speaking
    0.60
     blush
    0.60
     sounding
    0.58
    Act Density 0.119%

    No Known Activations