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

    Neuronpedia

    INDEX
    Explanations

    references to human existence and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _DSP
    -0.16
    $MESS
    -0.16
    ÑģÑĤÑĥп
    -0.15
    assy
    -0.15
    ima
    -0.14
    asd
    -0.14
     Personnel
    -0.14
    ếp
    -0.13
    edException
    -0.13
    athe
    -0.13
    POSITIVE LOGITS
    human
    0.20
     human
    0.19
     beings
    0.19
    -human
    0.18
    ادÛĮ
    0.17
    698
    0.16
    »
    0.16
     humans
    0.16
    θÏħ
    0.15
    ÑĤÑĢо
    0.15
    Act Density 0.220%

    No Known Activations