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

    Neuronpedia

    INDEX
    Explanations

    words related to specific activities or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccione
    -0.16
    vox
    -0.16
     Punch
    -0.15
    unner
    -0.15
    undan
    -0.15
     Oswald
    -0.14
    illet
    -0.14
     Crunch
    -0.14
    egrator
    -0.14
    анка
    -0.14
    POSITIVE LOGITS
    inburgh
    0.15
    -spinner
    0.15
    aler
    0.14
    luck
    0.14
    l
    0.14
    X
    0.13
    lá
    0.13
    luet
    0.13
     chai
    0.13
    ennon
    0.13
    Act Density 0.093%

    No Known Activations