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

    Neuronpedia

    INDEX
    Explanations

    dates or timeframes for future events or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to scheduled events or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isms
    -0.75
    Interstitial
    -0.72
    Austral
    -0.67
    Es
    -0.63
    angers
    -0.62
    natureconservancy
    -0.60
    ordinary
    -0.60
    Nature
    -0.58
    users
    -0.58
    drivers
    -0.58
    POSITIVE LOGITS
    onite
    0.77
    tenance
    0.69
    lein
    0.68
     Parenthood
    0.67
    eous
    0.65
    ĭ
    0.65
    abouts
    0.65
     externalToEVAOnly
    0.65
    hran
    0.64
    ¶æ
    0.64
    Act Density 0.025%

    No Known Activations