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

    Neuronpedia

    INDEX
    Explanations

    the use of personal pronouns indicating the speaker's perspective or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    غات
    -0.17
    تس
    -0.15
    rans
    -0.14
    mey
    -0.13
    rms
    -0.13
    arge
    -0.13
    erken
    -0.13
    oren
    -0.13
    een
    -0.13
     Ul
    -0.13
    POSITIVE LOGITS
    elas
    0.17
     ever
    0.17
    umbles
    0.16
    oton
    0.16
    rika
    0.15
    uzzer
    0.14
    -ever
    0.14
     encount
    0.14
    alion
    0.14
    ETCH
    0.14
    Act Density 0.044%

    No Known Activations