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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating a source or origin

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote a variety of items or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.82
    lyak
    -0.80
    faced
    -0.76
    certain
    -0.75
    ifix
    -0.73
    ItemTracker
    -0.73
    hai
    -0.71
    Study
    -0.71
    seek
    -0.70
    intosh
    -0.70
    POSITIVE LOGITS
     afar
    1.11
     whence
    0.88
     kindergarten
    0.85
     cradle
    0.76
     infancy
    0.75
     thence
    0.71
     inception
    0.70
     childhood
    0.69
     preschool
    0.66
     volleyball
    0.65
    Act Density 0.043%

    No Known Activations