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

    Neuronpedia

    INDEX
    Explanations

    references to official entities and scientific authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     apprec
    -0.14
    .Named
    -0.14
    /***************************************************************************↵
    -0.14
    á¿ĸ
    -0.13
    (named
    -0.13
    ë°©
    -0.13
    istrovstvÃŃ
    -0.13
    /Branch
    -0.13
    lé
    -0.13
    qe
    -0.13
    POSITIVE LOGITS
     across
    0.22
     familiar
    0.20
     involved
    0.19
     from
    0.19
     such
    0.18
     estimate
    0.17
    /operators
    0.17
     say
    0.16
     elsewhere
    0.16
     throughout
    0.16
    Act Density 0.093%

    No Known Activations