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

    Neuronpedia

    INDEX
    Explanations

    words related to innate qualities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "natural" and variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.83
    blers
    -0.75
    eters
    -0.72
     strapped
    -0.72
    apter
    -0.69
    raped
    -0.68
    rav
    -0.68
    enance
    -0.68
    iosyncr
    -0.67
    mercial
    -0.66
    POSITIVE LOGITS
    istic
    1.12
    izations
    1.05
    ization
    0.99
    ized
    0.97
    istically
    0.95
    isation
    0.95
    izes
    0.89
    izable
    0.87
     instinct
    0.87
    iste
    0.87
    Act Density 0.016%

    No Known Activations