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

    Neuronpedia

    INDEX
    Explanations

    patterns and structures in coding or programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zee
    -0.15
    enders
    -0.15
    elp
    -0.14
    edeki
    -0.14
    olit
    -0.14
    /preferences
    -0.14
    ¥¿
    -0.14
     assistir
    -0.14
    anggal
    -0.14
    lep
    -0.14
    POSITIVE LOGITS
    iras
    0.15
     Atlas
    0.14
     Sez
    0.14
    stown
    0.14
    AMI
    0.14
    .synthetic
    0.14
     Crush
    0.14
     Hak
    0.13
    eni
    0.13
    orton
    0.13
    Act Density 0.060%

    No Known Activations