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

    Neuronpedia

    INDEX
    Explanations

    references to conflict or tension involving individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lds
    -0.17
    ktor
    -0.16
    .synthetic
    -0.16
    worth
    -0.15
    kt
    -0.15
    KT
    -0.15
    auen
    -0.15
    елÑİ
    -0.14
    land
    -0.14
    linger
    -0.14
    POSITIVE LOGITS
    ½
    0.16
    teness
    0.16
    ToFit
    0.16
    anj
    0.15
    /screens
    0.15
    975
    0.15
    atoi
    0.14
    aya
    0.14
    eza
    0.14
    .InnerException
    0.14
    Act Density 0.813%

    No Known Activations