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

    Neuronpedia

    INDEX
    Explanations

    terms related to popularity and its variations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Nimbus
    -0.65
    ciente
    -0.63
    ள்
    -0.63
    scriptcase
    -0.59
    inaw
    -0.58
    skyline
    -0.57
    jooq
    -0.57
     cu
    -0.56
     numerus
    -0.56
    ValueStyle
    -0.56
    POSITIVE LOGITS
     Efq
    1.20
    ſelf
    1.09
     Theſe
    1.06
     leſs
    1.06
     pleaſure
    1.04
     whoſe
    1.03
    Portail
    1.02
     Majefty
    1.02
     Monfieur
    1.02
     ſche
    1.00
    Act Density 0.009%

    No Known Activations