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

    Neuronpedia

    INDEX
    Explanations

    question phrases that inquire about personal experiences or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illin
    -0.18
    vailability
    -0.15
    /pm
    -0.15
    (éĩij
    -0.14
    raki
    -0.14
    кÑĥÑģ
    -0.14
    ummings
    -0.14
    iros
    -0.14
    üf
    -0.14
     Circus
    -0.14
    POSITIVE LOGITS
    rett
    0.15
     wash
    0.15
    reich
    0.15
     Blank
    0.15
    pond
    0.14
    oon
    0.14
    Blank
    0.14
     Brock
    0.14
    ites
    0.14
    ingen
    0.14
    Act Density 0.042%

    No Known Activations