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

    Neuronpedia

    INDEX
    Explanations

    terms related to forgiveness and reconciliation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stub
    -0.17
    ifact
    -0.15
    shan
    -0.15
    /state
    -0.14
    INA
    -0.14
     if
    -0.14
    if
    -0.14
    issen
    -0.14
    quette
    -0.13
     Sail
    -0.13
    POSITIVE LOGITS
    alty
    0.20
    olvency
    0.16
    uiltin
    0.14
    .SelectCommand
    0.14
    .newInstance
    0.13
     Stre
    0.13
    åĿĽ
    0.13
     Hao
    0.13
    noop
    0.13
    ìĸ
    0.13
    Act Density 0.004%

    No Known Activations