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

    Neuronpedia

    INDEX
    Explanations

    terms related to success

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agine
    -0.66
     chairs
    -0.63
    inki
    -0.62
    odon
    -0.61
     iodine
    -0.61
    shapeshifter
    -0.60
     salt
    -0.60
     superflu
    -0.60
     vomit
    -0.58
     ox
    -0.58
    POSITIVE LOGITS
    ively
    1.12
    fully
    1.04
    ful
    0.99
    iveness
    0.90
    orship
    0.86
    full
    0.85
    fulness
    0.83
    ional
    0.82
    ivity
    0.80
    iences
    0.79
    Act Density 0.048%

    No Known Activations