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

    Neuronpedia

    INDEX
    Explanations

    references to demographics and health-related disparities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unal
    -0.15
    anvas
    -0.15
    regnum
    -0.14
    aber
    -0.14
    Ñħи
    -0.14
    lop
    -0.14
    sgi
    -0.14
    apl
    -0.14
    adele
    -0.13
    ANGLES
    -0.13
    POSITIVE LOGITS
     likelihood
    0.33
     lik
    0.31
     likely
    0.30
     twice
    0.28
     more
    0.28
     tend
    0.28
    likelihood
    0.28
     tends
    0.25
     unlikely
    0.24
    likely
    0.24
    Act Density 0.103%

    No Known Activations