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

    Neuronpedia

    INDEX
    Explanations

    references to minority groups and their experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hammond
    -0.18
    ASE
    -0.15
    acier
    -0.15
    semblies
    -0.15
    esk
    -0.14
     Pru
    -0.14
    s
    -0.14
    osci
    -0.14
    away
    -0.14
    ase
    -0.14
    POSITIVE LOGITS
    oreach
    0.16
    oken
    0.16
    plib
    0.16
    ovic
    0.15
    éŀ
    0.14
    uiltin
    0.14
    éij
    0.14
    weet
    0.14
    .prof
    0.14
     maur
    0.14
    Act Density 0.004%

    No Known Activations