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

    Neuronpedia

    INDEX
    Explanations

    references to evidence or validation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alom
    -0.17
    lle
    -0.15
    arium
    -0.14
    orama
    -0.14
    ÑĥÑģ
    -0.14
    mania
    -0.14
    ê»ĺ
    -0.14
    祥
    -0.14
    vre
    -0.14
    lernen
    -0.14
    POSITIVE LOGITS
    reading
    0.24
     pudding
    0.18
    edores
    0.17
    /dis
    0.17
    íıIJ
    0.16
    PU
    0.16
     transcend
    0.16
    read
    0.15
    reader
    0.15
    illard
    0.15
    Act Density 0.031%

    No Known Activations