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

    Neuronpedia

    INDEX
    Explanations

    expressions related to personal branding and professional integrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    753
    -0.17
    754
    -0.15
     tes
    -0.15
    964
    -0.15
    752
    -0.14
    995
    -0.14
    vey
    -0.14
    hsi
    -0.14
    asic
    -0.14
    242
    -0.14
    POSITIVE LOGITS
    atto
    0.16
    ebra
    0.16
    orden
    0.14
     háºŃu
    0.14
    ÃŃte
    0.14
    edor
    0.14
    obuf
    0.13
    olves
    0.13
    .prepend
    0.13
     TEMP
    0.13
    Act Density 0.102%

    No Known Activations