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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or groups in a supportive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.16
    eam
    -0.16
    .grpc
    -0.14
    ozo
    -0.14
    acht
    -0.14
    ington
    -0.14
    lein
    -0.14
     Tome
    -0.14
    loquent
    -0.14
    itude
    -0.13
    POSITIVE LOGITS
    /us
    0.27
    /her
    0.25
    zelf
    0.23
    self
    0.21
    /th
    0.18
    -même
    0.17
    iner
    0.17
     же
    0.16
    SELF
    0.16
    ÑĥÑīеÑģÑĤв
    0.15
    Act Density 0.156%

    No Known Activations