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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the significance or importance of an event or situation

    oai_token-act-pair · gpt-3.5-turbo

    references to the significance or impact of various "deals."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    İĭ
    -0.81
    asus
    -0.81
    prus
    -0.80
     Borough
    -0.75
    etheus
    -0.74
    antha
    -0.72
    oreAnd
    -0.72
    ¥ŀ
    -0.69
    ugal
    -0.68
    tein
    -0.67
    POSITIVE LOGITS
    deals
    0.83
     bec
    0.80
    INESS
    0.78
    breaker
    0.77
     breaker
    0.73
     deal
    0.72
    killer
    0.72
    ability
    0.71
    ership
    0.71
     surpr
    0.70
    Act Density 0.023%

    No Known Activations