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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss liability and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lingen
    -0.15
    coin
    -0.15
    838
    -0.15
    #SBATCH
    -0.15
    aron
    -0.14
    pir
    -0.14
     gamb
    -0.13
    _checkpoint
    -0.13
    .EventQueue
    -0.13
    asin
    -0.13
    POSITIVE LOGITS
     any
    0.17
     nor
    0.16
     Britt
    0.15
    SCO
    0.14
     anything
    0.14
    Ñıд
    0.14
    deaux
    0.14
    quis
    0.14
    rowave
    0.14
    isinden
    0.14
    Act Density 0.012%

    No Known Activations