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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions of mechanical components and their configurations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     chofe
    -0.65
     poffe
    -0.63
     reafon
    -0.63
     deſt
    -0.63
    SharedCtor
    -0.61
     fhew
    -0.59
    gonic
    -0.59
     Monfieur
    -0.57
     uſed
    -0.56
     Gallimard
    -0.55
    POSITIVE LOGITS
     pattern
    0.63
     '\\;'
    0.62
     detail
    0.60
     patterns
    0.60
    elemField
    0.57
    érien
    0.57
    enumerate
    0.56
    detail
    0.54
     OMITBAD
    0.54
     Patterns
    0.53
    Act Density 0.132%

    No Known Activations