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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns and references to personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTO
    -0.16
    vt
    -0.15
    arch
    -0.14
     advanced
    -0.14
    ãĥªãĥ³
    -0.14
     round
    -0.14
     strategy
    -0.14
     inside
    -0.14
     exact
    -0.13
     quarters
    -0.13
    POSITIVE LOGITS
    @student
    0.17
    بس
    0.15
    ostat
    0.15
    ControlItem
    0.15
    viar
    0.15
    oningen
    0.15
     poil
    0.15
    ableObject
    0.15
    XMLLoader
    0.15
    .blob
    0.15
    Act Density 0.002%

    No Known Activations