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

    Neuronpedia

    INDEX
    Explanations

    words related to concluding statements or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.90
    MigrationBuilder
    -0.75
    oa̍t
    -0.72
    المناصب
    -0.72
    -0.71
     betweenstory
    -0.66
     мәкал
    -0.65
    ConstraintMaker
    -0.63
     вікі
    -0.62
    CopyWith
    -0.61
    POSITIVE LOGITS
     Vielen
    0.53
    iza
    0.51
    IZA
    0.51
    大満足
    0.49
     Other
    0.48
    SuspendLayout
    0.48
    ANCED
    0.47
    tso
    0.47
     Overview
    0.46
     Thank
    0.46
    Act Density 0.132%

    No Known Activations