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

    Neuronpedia

    INDEX
    Explanations

    phrases related to defining or determining something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "constitute" and its variations in legal or formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ithing
    -0.69
     Bald
    -0.67
    enger
    -0.65
    hner
    -0.64
     preacher
    -0.62
    ITCH
    -0.61
    hy
    -0.61
    hon
    -0.59
     Freddie
    -0.58
    ying
    -0.58
    POSITIVE LOGITS
    aldehyde
    0.84
    rarily
    0.82
    idable
    0.82
    itutes
    0.80
    ALLY
    0.76
    ally
    0.76
    untarily
    0.74
    amate
    0.72
    eering
    0.72
    rary
    0.71
    Act Density 0.018%

    No Known Activations