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

    Neuronpedia

    INDEX
    Explanations

    phrases related to potential outcomes or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to expectations, possibilities, and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aughs
    -0.76
    enhagen
    -0.70
    inho
    -0.70
     CrossRef
    -0.70
     Braun
    -0.69
     Sutherland
    -0.69
     Keller
    -0.64
     Debor
    -0.64
     Charity
    -0.64
     Bellev
    -0.63
    POSITIVE LOGITS
     whatsoever
    1.73
     imaginable
    1.02
     except
    0.88
     besides
    0.85
     thereof
    0.84
    soever
    0.81
     semblance
    0.78
     pertaining
    0.75
     conceivable
    0.75
     deemed
    0.73
    Act Density 0.198%

    No Known Activations