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

    Neuronpedia

    INDEX
    Explanations

    negative phrases or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -ÑĤо
    -0.17
    reed
    -0.17
    unter
    -0.16
    -vous
    -0.16
     же
    -0.15
    %s
    -0.15
    -looking
    -0.15
    सम
    -0.15
    alog
    -0.15
    bourg
    -0.14
    POSITIVE LOGITS
    /+
    0.23
    /-
    0.18
    ÂĢÂ
    0.18
    webkit
    0.18
    _-
    0.17
    .-
    0.16
    ãĢĭ
    0.15
    vs
    0.15
    Âĸ
    0.15
    vas
    0.14
    Act Density 0.274%

    No Known Activations