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

    Neuronpedia

    INDEX
    Explanations

    the presence of numerical references or values

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.90
    ])).
    -0.72
     disambiguazione
    -0.68
    ]));
    -0.65
    WithMany
    -0.63
    Vidite
    -0.63
    Bleeding
    -0.62
     isSet
    -0.61
     ivelany
    -0.61
     ErrInvalid
    -0.61
    POSITIVE LOGITS
    正直
    0.52
    miary
    0.49
    ConstraintMaker
    0.48
     فريبيس
    0.47
     nationaux
    0.46
    анс
    0.45
     assistir
    0.44
     quedarse
    0.44
    ram
    0.44
    いえば
    0.44
    Act Density 0.005%

    No Known Activations