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

    Neuronpedia

    INDEX
    Explanations

    comparisons of likelihood between genders or groups in relation to their behaviors or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.16
    avis
    -0.15
    enus
    -0.15
    abi
    -0.15
    asse
    -0.14
    enos
    -0.14
    ig
    -0.14
    æģ¯
    -0.13
    anca
    -0.13
    asl
    -0.13
    POSITIVE LOGITS
    akov
    0.17
     than
    0.16
    acen
    0.16
    -than
    0.16
    umber
    0.15
    uzzi
    0.15
    ÏĢÏĮ
    0.15
    umbn
    0.15
    ednou
    0.14
    á»ĵn
    0.14
    Act Density 0.065%

    No Known Activations