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

    Neuronpedia

    INDEX
    Explanations

    references to physical trainers and training activities

    oai_token-act-pair · gpt-3.5-turbo

    references to trainers and instructors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Democr
    -0.73
     Virgin
    -0.69
    carbon
    -0.67
     Papers
    -0.66
     1861
    -0.66
     Constitutional
    -0.66
     Rosen
    -0.64
     Gutenberg
    -0.64
     Dickens
    -0.63
     Socialism
    -0.62
    POSITIVE LOGITS
     trainer
    3.95
     trainers
    3.58
     Trainer
    2.59
     instructor
    1.79
     instructors
    1.62
    training
    1.53
    Training
    1.52
     training
    1.52
     Training
    1.46
     therapist
    1.43
    Act Density 0.017%

    No Known Activations