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

    Neuronpedia

    INDEX
    Explanations

    expressions related to physical or emotional distress and discomfort

    oai_token-act-pair · gpt-3.5-turbo

    words related to negative experiences or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IFT
    -0.67
     Breach
    -0.63
    ogical
    -0.62
     happening
    -0.59
     empt
    -0.58
    çĶ
    -0.58
    )].
    -0.58
     Bring
    -0.58
     Line
    -0.57
     Infinite
    -0.57
    POSITIVE LOGITS
    aned
    4.19
    eded
    1.04
    anol
    1.03
    ane
    0.95
    bered
    0.95
    aved
    0.93
    aired
    0.91
    anes
    0.91
    anism
    0.86
    anan
    0.84
    Act Density 0.018%

    No Known Activations