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

    Neuronpedia

    INDEX
    Explanations

    terms related to excess or overabundance in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Karla
    -0.74
     Plummer
    -0.71
     marten
    -0.69
    OGND
    -0.67
    JTable
    -0.66
     Plat
    -0.63
     Cly
    -0.63
    DATABASES
    -0.63
    BeginContext
    -0.62
    neurial
    -0.61
    POSITIVE LOGITS
     Excess
    1.07
    Excess
    1.00
     excess
    0.96
    excess
    0.85
     excesses
    0.82
     excès
    0.82
     circonst
    0.81
     EXC
    0.80
     dư
    0.80
     Surplus
    0.80
    Act Density 0.014%

    No Known Activations