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

    Neuronpedia

    INDEX
    Explanations

    terms related to various forms of "ness" or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    excellents
    -0.69
    arshal
    -0.65
     solares
    -0.64
     rubrique
    -0.62
    odenal
    -0.62
     tấn
    -0.62
    richtet
    -0.62
    ot
    -0.61
    Documented
    -0.60
    REGISTER
    -0.60
    POSITIVE LOGITS
    teness
    1.02
    fulness
    0.98
    cency
    0.92
    ogeneity
    0.89
    Carcinogenicity
    0.89
    ctility
    0.87
    icity
    0.86
    IGENCE
    0.85
    tility
    0.84
    ibility
    0.83
    Act Density 0.823%

    No Known Activations