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

    Neuronpedia

    INDEX
    Explanations

    phrases related to prior job experiences and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atten
    -0.15
    fw
    -0.15
    anim
    -0.15
    orman
    -0.15
    lich
    -0.15
    animate
    -0.14
    esin
    -0.14
    bou
    -0.14
    icha
    -0.14
     gate
    -0.14
    POSITIVE LOGITS
     ierr
    0.16
    gos
    0.15
    arness
    0.15
    äºĭ
    0.14
    olvers
    0.14
     sill
    0.14
     reap
    0.14
    etes
    0.14
    byss
    0.14
    gia
    0.14
    Act Density 0.017%

    No Known Activations