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

    Neuronpedia

    INDEX
    Explanations

    words related to intention or purpose

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to intent and intentions behind actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cit
    -0.77
    visor
    -0.73
    visors
    -0.68
    java
    -0.64
     Jub
    -0.64
     Tycoon
    -0.63
     Solitaire
    -0.63
     beds
    -0.63
     Cham
    -0.62
     Britann
    -0.61
    POSITIVE LOGITS
    ality
    1.03
    ful
    1.00
    fulness
    0.98
    edly
    0.89
    ually
    0.88
    lessly
    0.85
    uality
    0.82
    ual
    0.81
    FUL
    0.80
    teness
    0.79
    Act Density 0.037%

    No Known Activations