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

    Neuronpedia

    INDEX
    Explanations

    references to fairness and fairness-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elho
    -0.20
    omic
    -0.17
    CHIP
    -0.16
    ering
    -0.15
    ova
    -0.15
    endor
    -0.15
    owo
    -0.14
    ote
    -0.14
    chin
    -0.14
    chers
    -0.14
    POSITIVE LOGITS
    yt
    0.31
    ground
    0.27
    weather
    0.26
    grounds
    0.26
    fax
    0.24
    er
    0.22
    hart
    0.19
    iez
    0.18
    mount
    0.17
    bnb
    0.17
    Act Density 0.026%

    No Known Activations