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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a suggested action

    oai_token-act-pair · gpt-3.5-turbo

    phrases or clauses expressing purpose or intention, typically indicated by the phrase "so that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARK
    -0.68
    ãĤ´ãĥ³
    -0.62
     Exodus
    -0.61
    PRESS
    -0.60
    ART
    -0.60
    DAQ
    -0.59
    Plus
    -0.59
    AND
    -0.58
    arag
    -0.58
    ãĥ¡
    -0.57
    POSITIVE LOGITS
    uces
    0.75
     they
    0.74
     whoever
    0.69
     nobody
    0.68
     maxim
    0.68
    ndra
    0.67
     persists
    0.66
    ancial
    0.64
     we
    0.62
    pload
    0.62
    Act Density 0.052%

    No Known Activations