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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to hair

    oai_token-act-pair · gpt-3.5-turbo

    references to hair

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Angelo
    -0.72
    reb
    -0.70
    Columb
    -0.70
    Pac
    -0.70
     Overse
    -0.70
    sov
    -0.68
    venants
    -0.68
    ZI
    -0.66
    Ëľ
    -0.65
     LX
    -0.64
    POSITIVE LOGITS
     hair
    3.61
     Hair
    2.70
     hairs
    2.70
     hairst
    2.29
    hair
    2.13
     hairc
    1.95
     haircut
    1.94
     beard
    1.85
     wig
    1.76
     curly
    1.70
    Act Density 0.025%

    No Known Activations