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

    Neuronpedia

    INDEX
    Explanations

    indicative verbs and phrases related to actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isle
    -0.17
    rts
    -0.16
    rosse
    -0.15
    ace
    -0.15
     competitors
    -0.14
    arta
    -0.14
    uset
    -0.14
    ë¦
    -0.13
    psc
    -0.13
    uli
    -0.13
    POSITIVE LOGITS
    angu
    0.15
    DataExchange
    0.15
    apol
    0.15
    миÑĤ
    0.15
    ãĥĬãĥ«
    0.15
    vrier
    0.14
     EntityState
    0.14
    /rss
    0.14
    .rabbit
    0.14
    :↵↵↵↵↵↵
    0.13
    Act Density 0.052%

    No Known Activations