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

    Neuronpedia

    INDEX
    Explanations

    references to individuals in athletic training roles

    oai_token-act-pair · gpt-3.5-turbo

    references to trainers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lishes
    -0.75
    mits
    -0.71
    sm
    -0.66
    izons
    -0.66
     sill
    -0.65
    pty
    -0.64
    rought
    -0.63
    article
    -0.62
    gets
    -0.61
    bern
    -0.61
    POSITIVE LOGITS
     trainer
    1.32
     trainers
    1.17
     Trainer
    1.05
     instructors
    0.77
     instructor
    0.75
    ="#
    0.73
     Instructor
    0.71
     bred
    0.69
     endors
    0.68
    caster
    0.68
    Act Density 0.009%

    No Known Activations