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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions or temporal relationships

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a minimum or a threshold

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄŁ
    -0.80
    igr
    -0.76
    ament
    -0.72
    ursday
    -0.72
    ricks
    -0.70
    iard
    -0.70
     hurd
    -0.67
    pie
    -0.67
    uesday
    -0.67
     Grimes
    -0.66
    POSITIVE LOGITS
     Marketable
    0.92
     outright
    0.74
    Downloadha
    0.70
     equivalents
    0.70
    acular
    0.69
    ifice
    0.68
    acle
    0.66
     vice
    0.66
     pretended
    0.65
     equivalent
    0.65
    Act Density 0.044%

    No Known Activations