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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating someone or something being put into a specific position or situation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "placed" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -1.00
    MED
    -0.61
    issance
    -0.58
    bie
    -0.58
    magic
    -0.57
    reader
    -0.57
     Moder
    -0.56
     conver
    -0.56
    vine
    -0.56
     Angus
    -0.56
    POSITIVE LOGITS
    ngth
    0.86
    arnaev
    0.85
    sembly
    0.85
     Parenthood
    0.81
    holders
    0.79
     plac
    0.73
     placed
    0.71
    ipl
    0.71
    aution
    0.70
    uate
    0.70
    Act Density 0.026%

    No Known Activations