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

    Neuronpedia

    INDEX
    Explanations

    terms that convey utility or helpfulness in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.67
     gynhyrchwyd
    -0.65
     honours
    -0.59
     ég
    -0.59
    cydow
    -0.59
    stdc
    -0.56
    oliber
    -0.56
     intonation
    -0.55
    ViewImports
    -0.54
     Mist
    -0.54
    POSITIVE LOGITS
     useful
    1.52
    useful
    1.41
     Useful
    1.40
    Useful
    1.30
     útil
    1.14
     utile
    1.11
    Helpful
    1.10
     útiles
    1.10
     useless
    1.08
     helpful
    1.04
    Act Density 0.059%

    No Known Activations