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

    Neuronpedia

    INDEX
    Explanations

    terms related to exclusions and limitations in agreements or estimations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DisplayName
    -0.16
    haps
    -0.15
    ix
    -0.14
    pe
    -0.14
    dro
    -0.13
    ик
    -0.13
    ag
    -0.13
     Dich
    -0.13
    oping
    -0.13
     Scalars
    -0.13
    POSITIVE LOGITS
    ugin
    0.19
    indrical
    0.16
    itom
    0.15
    ::__
    0.15
    ensis
    0.15
    erca
    0.15
    chez
    0.14
    ensi
    0.14
    otros
    0.14
     whe
    0.14
    Act Density 0.266%

    No Known Activations