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

    Neuronpedia

    INDEX
    Explanations

    verbs related to physical or metaphorical actions

    oai_token-act-pair · gpt-3.5-turbo

    active verbs that suggest significant actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    been
    -0.61
    arta
    -0.60
    bie
    -0.54
    yond
    -0.53
    venge
    -0.53
    tis
    -0.53
    por
    -0.53
    yet
    -0.52
    externalActionCode
    -0.51
    esa
    -0.51
    POSITIVE LOGITS
    nesday
    0.63
     unsuccessfully
    0.59
     showc
    0.53
    ãĤ¤ãĥĪ
    0.53
     pione
    0.52
     tremend
    0.52
    Ô
    0.48
    uled
    0.48
     extensively
    0.47
    ĸļ
    0.45
    Act Density 0.755%

    No Known Activations