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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking control or responsibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to charge or responsibility in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Moroc
    -0.69
     referen
    -0.62
    ãĥ¼ãĥĨãĤ£
    -0.58
     corrid
    -0.54
    estyles
    -0.51
    edIn
    -0.50
     thous
    -0.46
    acebook
    -0.46
    ãĤ´ãĥ³
    -0.46
    ãĥĩãĤ£
    -0.46
    POSITIVE LOGITS
     largeDownload
    0.45
    mosp
    0.44
    rous
    0.43
    othes
    0.43
    cess
    0.43
    ealous
    0.42
    immer
    0.42
    urrection
    0.41
     stead
    0.41
    ctive
    0.41
    Act Density 4.099%

    No Known Activations