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

    Neuronpedia

    INDEX
    Explanations

    words related to identification or designation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icoot
    -0.81
    Demografía
    -0.80
    łgorzata
    -0.78
    ggak
    -0.77
    outchouc
    -0.77
    antwo
    -0.77
    ypus
    -0.76
     Comstock
    -0.75
     Butterfield
    -0.75
    harusnya
    -0.74
    POSITIVE LOGITS
    en
    1.33
    fen
    1.24
    eden
    1.21
    hen
    1.19
    EN
    1.16
    zen
    1.11
    nen
    1.09
    ken
    1.05
    aten
    1.04
    wen
    1.03
    Act Density 0.470%

    No Known Activations