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

    Neuronpedia

    INDEX
    Explanations

    concepts related to justice and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dymyr
    -0.65
    حديد
    -0.59
    zuführen
    -0.58
     numberWith
    -0.57
    kamen
    -0.52
    gbaar
    -0.51
     Meksiku
    -0.51
     يتيمه
    -0.51
    romycin
    -0.51
    toThrow
    -0.48
    POSITIVE LOGITS
     we
    0.89
     they
    0.84
     you
    0.82
    TypedDataSet
    0.76
     jakie
    0.76
     mitä
    0.68
    InjectAttribute
    0.66
     &___
    0.66
     jaką
    0.64
     auquel
    0.63
    Act Density 0.749%

    No Known Activations