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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions that involve physical manipulation or movement

    oai_token-act-pair · gpt-3.5-turbo

    word segments and suffixes related to diminutive or trivializing forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioch
    -0.80
    Downloadha
    -0.79
    govtrack
    -0.78
    ĪĴ
    -0.78
    omes
    -0.72
    hemy
    -0.72
    uries
    -0.69
    vernment
    -0.68
    ß
    -0.67
     Extrem
    -0.67
    POSITIVE LOGITS
    tle
    1.36
    butt
    1.23
    mont
    0.95
    fish
    0.93
    estones
    0.88
    ty
    0.87
    bum
    0.86
    brate
    0.85
    pole
    0.85
    brates
    0.85
    Act Density 0.012%

    No Known Activations