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

    Neuronpedia

    INDEX
    Explanations

    references to violent or destructive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ssel
    -0.17
    zial
    -0.16
    UNE
    -0.16
    å°ıå§IJ
    -0.15
    esan
    -0.14
    izabeth
    -0.14
    ìļ©
    -0.14
     crow
    -0.14
    umo
    -0.14
    ambre
    -0.13
    POSITIVE LOGITS
    oes
    0.15
    itution
    0.15
    AGED
    0.15
    ivals
    0.14
    flush
    0.14
    ingly
    0.14
     reducers
    0.14
    uarios
    0.14
    fold
    0.13
     clearTimeout
    0.13
    Act Density 0.057%

    No Known Activations