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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate seeking information or discovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onto
    -0.17
    itsu
    -0.17
     zoekt
    -0.15
    kel
    -0.14
    uments
    -0.14
    ito
    -0.14
    anzi
    -0.14
    innie
    -0.13
    ched
    -0.13
    velop
    -0.13
    POSITIVE LOGITS
     about
    0.23
    _about
    0.18
    about
    0.16
    strcasecmp
    0.16
    zia
    0.14
    braco
    0.14
     bout
    0.14
    θι
    0.14
     how
    0.14
    asin
    0.14
    Act Density 0.015%

    No Known Activations