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

    Neuronpedia

    INDEX
    Explanations

    expressions of intent or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indsight
    -0.08
    atern
    -0.07
    oj
    -0.07
    uj
    -0.07
    inz
    -0.07
    ëį°ìĿ´íĬ¸
    -0.07
    765
    -0.07
    uintptr
    -0.07
    ateria
    -0.07
    onaut
    -0.07
    POSITIVE LOGITS
     harm
    0.09
    fully
    0.09
     Harm
    0.09
    ioned
    0.07
    lessly
    0.07
    estate
    0.07
     intend
    0.06
     trouble
    0.06
    -mean
    0.06
    INGLE
    0.06
    Act Density 0.005%

    No Known Activations