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

    Neuronpedia

    INDEX
    Explanations

    2nd person pronouns and addressing the reader directly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    duc
    -0.15
    alo
    -0.15
    urga
    -0.15
    assed
    -0.15
    elon
    -0.14
    zs
    -0.14
    elu
    -0.14
     Merry
    -0.14
    anova
    -0.14
    ombo
    -0.14
    POSITIVE LOGITS
     OP
    0.16
    ä»ģ
    0.15
     mentioned
    0.15
     luck
    0.15
     posted
    0.14
    mentioned
    0.14
     bang
    0.14
     should
    0.14
     Stub
    0.13
     Voor
    0.13
    Act Density 0.053%

    No Known Activations