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

    Neuronpedia

    INDEX
    Explanations

    references to specific items or tools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.95
     esternos
    -0.91
     Normdatei
    -0.88
     raiſ
    -0.88
    '},
    -0.86
     itſelf
    -0.86
     faſt
    -0.86
     ſind
    -0.86
    ']):
    -0.86
    Personensuche
    -0.85
    POSITIVE LOGITS
     
    0.52
     same
    0.47
     now
    0.46
    </em>
    0.45
     and
    0.45
    .
    0.45
    alibaba
    0.44
     -
    0.44
     later
    0.44
     as
    0.43
    Act Density 0.525%

    No Known Activations