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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical disruption or overthrowing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iola
    -0.15
     Arbor
    -0.15
     arz
    -0.15
    orama
    -0.14
    leaders
    -0.14
     PURE
    -0.14
    filt
    -0.14
    ocha
    -0.14
     ara
    -0.13
    ottage
    -0.13
    POSITIVE LOGITS
    OKIE
    0.17
    isti
    0.16
    át
    0.15
    ITTER
    0.15
    hte
    0.15
    Gratis
    0.14
    _CALLBACK
    0.14
    ke
    0.14
     Throw
    0.14
    ÑĪкÑĥ
    0.14
    Act Density 0.109%

    No Known Activations