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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and their associated actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     certainly
    -0.08
    ubo
    -0.07
    riangle
    -0.07
    oit
    -0.07
     adalah
    -0.07
    otts
    -0.07
    anter
    -0.07
    ashtra
    -0.07
    ussen
    -0.06
     however
    -0.06
    POSITIVE LOGITS
    upon
    0.08
     slightest
    0.07
    uzz
    0.07
    ÅĻad
    0.06
     suddenly
    0.06
    Å¡et
    0.06
    gu
    0.06
    uz
    0.06
    aging
    0.06
     tiener
    0.06
    Act Density 0.026%

    No Known Activations