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

    Neuronpedia

    INDEX
    Explanations

    expressions of opinion or emphasis regarding actions and results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hte
    -0.16
    boom
    -0.15
    eph
    -0.15
    dez
    -0.15
    _PAYLOAD
    -0.14
    bed
    -0.14
    oins
    -0.14
     Credits
    -0.14
     inn
    -0.14
     кÑĢа
    -0.13
    POSITIVE LOGITS
    اÙĪت
    0.16
    anya
    0.16
     Volk
    0.15
    apos
    0.15
    à¥Ĥन
    0.15
    uppy
    0.15
    >[]
    0.14
    ãģĹãĤĥ
    0.14
    agrant
    0.14
    stry
    0.14
    Act Density 0.004%

    No Known Activations