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

    Neuronpedia

    INDEX
    Explanations

    themes of accountability and responsibility in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ixa
    -0.17
    ghi
    -0.15
     spis
    -0.15
    /Table
    -0.14
    uzzi
    -0.14
    ØŃØ©
    -0.14
    Äįen
    -0.14
    Injector
    -0.14
    vox
    -0.14
    커
    -0.14
    POSITIVE LOGITS
    unte
    0.17
     fault
    0.16
     mal
    0.15
     prior
    0.15
    SEL
    0.15
     own
    0.14
    isko
    0.14
    icaret
    0.13
     Baghd
    0.13
    hr
    0.13
    Act Density 0.296%

    No Known Activations