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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the effectiveness and implications of actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    protoimpl
    -0.65
    tvguidetime
    -0.63
    ReusableCell
    -0.58
    MigrationBuilder
    -0.58
     disambiguazione
    -0.57
     Ouv
    -0.56
     unknownFields
    -0.54
    specially
    -0.54
     auffi
    -0.53
     طی
    -0.53
    POSITIVE LOGITS
     without
    0.68
     base
    0.58
     if
    0.58
    헌
    0.55
     Plan
    0.53
     Without
    0.51
     Sec
    0.49
    いても
    0.48
    Without
    0.48
    いくら
    0.48
    Act Density 0.200%

    No Known Activations