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

    Neuronpedia

    INDEX
    Explanations

    dash or hyphenated constructs indicating contrasts or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     мәкал
    -0.75
    namese
    -0.70
    substack
    -0.68
     &___
    -0.68
     MatDialog
    -0.66
    ſs
    -0.66
     Fij
    -0.65
    reras
    -0.64
     Elizabethan
    -0.63
     oaths
    -0.63
    POSITIVE LOGITS
    enderror
    0.96
    ScopeManager
    0.83
    ，
    0.65
    parsedMessage
    0.62
    설
    0.59
    bo
    0.59
    WireFormat
    0.58
    Hozzáférés
    0.58
     PublicKey
    0.58
     but
    0.57
    Act Density 0.068%

    No Known Activations