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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or expressions of frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iq
    -0.15
    stm
    -0.15
    avig
    -0.15
    actionDate
    -0.15
    980
    -0.14
    ipt
    -0.14
    orns
    -0.14
    jit
    -0.14
    jt
    -0.14
    024
    -0.14
    POSITIVE LOGITS
    tem
    0.20
    rog
    0.19
    rop
    0.18
    hip
    0.18
    ear
    0.17
    ide
    0.17
    aph
    0.17
    ink
    0.17
    ador
    0.16
    abor
    0.16
    Act Density 0.056%

    No Known Activations