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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evaluation or assessment of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "hold up" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascus
    -0.64
    cest
    -0.63
    cean
    -0.63
     [/
    -0.62
    sect
    -0.62
    furt
    -0.61
    enfranch
    -0.59
    [/
    -0.59
     bis
    -0.58
    ceivable
    -0.57
    POSITIVE LOGITS
    river
    0.91
    oppable
    0.78
    rights
    0.76
    adesh
    0.74
    puff
    0.73
     clipboard
    0.73
    TPP
    0.71
    inar
    0.71
    asar
    0.71
    CHAT
    0.67
    Act Density 0.019%

    No Known Activations