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

    Neuronpedia

    INDEX
    Explanations

    expressions of dissatisfaction or disenfranchisement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wise
    -0.16
    urally
    -0.15
    icer
    -0.15
     prod
    -0.14
    hin
    -0.14
    kiye
    -0.14
     bras
    -0.14
    anness
    -0.14
    ically
    -0.13
     Submitted
    -0.13
    POSITIVE LOGITS
    enuous
    0.21
    chantment
    0.19
    agement
    0.19
    AGEMENT
    0.17
    gregated
    0.16
    emma
    0.16
    .getFloat
    0.15
     vá»įng
    0.15
    /dis
    0.15
    gregation
    0.15
    Act Density 0.017%

    No Known Activations