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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of a supporting party or source

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    الإنجليزية
    -0.74
    help
    -0.69
     GIP
    -0.67
    InstrumentedTest
    -0.66
    IsContent
    -0.66
     BSEB
    -0.65
     Bewußt
    -0.63
     ACI
    -0.63
    ťaž
    -0.62
     beaver
    -0.62
    POSITIVE LOGITS
     the
    0.89
     an
    0.78
     a
    0.69
     another
    0.61
     with
    0.59
    Demikian
    0.57
     all
    0.56
     both
    0.56
     two
    0.55
     Berikut
    0.54
    Act Density 0.316%

    No Known Activations