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

    Neuronpedia

    INDEX
    Explanations

    words related to destructive actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñıж
    -0.17
    é®®
    -0.15
    obraz
    -0.15
    ulia
    -0.15
    ason
    -0.15
     stab
    -0.15
    &C
    -0.15
    imest
    -0.14
    edis
    -0.14
    eka
    -0.14
    POSITIVE LOGITS
    uther
    0.19
    :host
    0.16
    aversal
    0.16
    706
    0.14
     Acquisition
    0.14
    zÃŃ
    0.14
    nf
    0.14
    ZY
    0.14
    è´
    0.13
     Gibson
    0.13
    Act Density 0.341%

    No Known Activations