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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs indicating actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahon
    -0.66
     recall
    -0.63
    erno
    -0.60
     rematch
    -0.60
     âĵĺ
    -0.58
     anniversary
    -0.57
     directory
    -0.56
    wall
    -0.56
    etc
    -0.56
     antioxid
    -0.55
    POSITIVE LOGITS
    hes
    1.29
     formerly
    1.12
     previously
    1.05
    hers
    0.97
     originally
    0.96
     recently
    0.96
    wolves
    0.88
    itates
    0.84
     hitherto
    0.79
    wolf
    0.78
    Act Density 0.433%

    No Known Activations