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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADM
    -0.17
     zbyt
    -0.16
    pty
    -0.15
     ADM
    -0.15
    036
    -0.14
    adh
    -0.14
     Downing
    -0.14
    ummer
    -0.14
    edia
    -0.14
    idot
    -0.13
    POSITIVE LOGITS
    amente
    0.15
    hire
    0.15
    åŃĿ
    0.14
    ÅĻej
    0.14
    åij¨å¹´
    0.14
     reg
    0.14
    ë°ľ
    0.14
    MODEL
    0.13
    ropp
    0.13
    wald
    0.13
    Act Density 0.000%

    No Known Activations