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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "mad" in different contexts, such as emotions, actions, and descriptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mad" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chnology
    -0.82
    ãģ¯
    -0.79
    etitive
    -0.76
    OPLE
    -0.75
    soDeliveryDate
    -0.74
    çĦ
    -0.70
    apers
    -0.70
    oldown
    -0.70
    ylon
    -0.69
    odcast
    -0.69
    POSITIVE LOGITS
    agascar
    1.12
    rid
    1.04
    der
    0.85
    cap
    0.80
    mad
    0.79
    bol
    0.77
    ness
    0.77
     dash
    0.75
    iate
    0.75
     mad
    0.75
    Act Density 0.009%

    No Known Activations