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

    Neuronpedia

    INDEX
    Explanations

    sentences indicating exclusivity or the presence of specific individuals or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yt
    -0.16
     sid
    -0.15
    Ïģκ
    -0.15
    anco
    -0.15
    osc
    -0.15
     Seit
    -0.15
    kre
    -0.15
    692
    -0.14
     sh
    -0.14
    OSC
    -0.14
    POSITIVE LOGITS
    daf
    0.16
    ¬¸
    0.15
    ongan
    0.15
    upe
    0.15
    ngr
    0.14
    .Suppress
    0.14
     ëıĮ
    0.14
    /packages
    0.14
    orre
    0.14
    uação
    0.14
    Act Density 0.253%

    No Known Activations