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

    Neuronpedia

    INDEX
    Explanations

    statements that introduce conclusions or significant ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mep
    -0.98
     Coton
    -0.98
     Frankie
    -0.96
     CPF
    -0.95
     Eureka
    -0.93
     PVP
    -0.93
     Colette
    -0.93
     Bernadette
    -0.92
     Sarg
    -0.91
    eable
    -0.90
    POSITIVE LOGITS
    ly
    1.04
    ς
    0.84
     dần
    0.79
    cassert
    0.78
    جستارهای
    0.78
    maßen
    0.77
     thus
    0.77
    ième
    0.76
    دانشنامهٔ
    0.76
    ⁎
    0.74
    Act Density 0.107%

    No Known Activations