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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to political and social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -1.01
     الحره
    -0.84
    SourceChecksum
    -0.71
     propOrder
    -0.70
    Enllaces
    -0.68
     ویکی‌آمباردا
    -0.68
    DebuggerNonUser
    -0.68
     nahilalakip
    -0.68
    ILayout
    -0.68
    tagHelperRunner
    -0.67
    POSITIVE LOGITS
     speaking
    0.80
     parlant
    0.76
     hablando
    0.72
     Speaking
    0.68
     significant
    0.67
     falando
    0.64
     sound
    0.59
    sound
    0.59
    Speaking
    0.59
     parlando
    0.58
    Act Density 0.225%

    No Known Activations