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

    Neuronpedia

    INDEX
    Explanations

    German words

    oai_token-act-pair · gpt-3.5-turbo

    words related to emotional states or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wrestling
    -0.75
     Flavoring
    -0.74
    Warning
    -0.70
    WARE
    -0.70
    Wheel
    -0.69
    Downloadha
    -0.69
    STEP
    -0.68
    Page
    -0.67
    Bright
    -0.67
    é»Ĵ
    -0.67
    POSITIVE LOGITS
    cd
    0.82
    udes
    0.81
    ude
    0.79
    arse
    0.78
    qq
    0.75
    rent
    0.75
    ande
    0.73
    ensis
    0.73
    uni
    0.73
    rog
    0.73
    Act Density 0.200%

    No Known Activations