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

    Neuronpedia

    INDEX
    Explanations

    terms related to brokenness or errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ."],
    -0.56
    "),
    -0.56
    WireFormat
    -0.55
    ()]
    -0.55
    __);
    -0.55
     cioè
    -0.53
    zky
    -0.52
     racines
    -0.52
    )"),
    -0.52
     gâ
    -0.51
    POSITIVE LOGITS
     msg
    0.83
     BRO
    0.80
    BRO
    0.75
    msg
    0.70
    Tikang
    0.70
    tvguidetime
    0.69
     обез
    0.66
     broken
    0.65
     Bro
    0.65
    ########.
    0.65
    Act Density 0.036%

    No Known Activations