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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific nouns or names, often starting with a capital letter

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names and terms associated with notable movies or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸ¬
    -0.87
     indo
    -0.82
    hetic
    -0.66
    iments
    -0.66
     partName
    -0.65
    FTWARE
    -0.65
    âĸ¬âĸ¬
    -0.65
    hetically
    -0.64
    iment
    -0.63
    eco
    -0.62
    POSITIVE LOGITS
    shots
    0.81
    iewicz
    0.80
    Leaks
    0.73
    antha
    0.71
    roots
    0.71
    lord
    0.71
    shot
    0.65
    urrection
    0.64
     Wick
    0.63
    steps
    0.63
    Act Density 0.052%

    No Known Activations