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

    Neuronpedia

    INDEX
    Explanations

    modal verbs or phrases indicating impossibility or necessity

    oai_token-act-pair · gpt-3.5-turbo

    negation or phrases indicating impossibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.58
    CI
    -0.57
    iens
    -0.56
     Cutter
    -0.55
    gat
    -0.55
    imity
    -0.54
     inspecting
    -0.53
     Gat
    -0.51
     naming
    -0.51
    Person
    -0.51
    POSITIVE LOGITS
     be
    1.19
     possibly
    1.12
     withstand
    0.98
     feas
    0.97
     happen
    0.94
     plaus
    0.92
     exist
    0.92
    possibly
    0.89
     occur
    0.89
     Possibly
    0.86
    Act Density 0.108%

    No Known Activations