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

    Neuronpedia

    INDEX
    Explanations

    instances of individuals or professionals in various fields

    oai_token-act-pair · gpt-3.5-turbo

    the article "a" preceding various professions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Contents
    -0.89
    SIGN
    -0.74
    eye
    -0.71
    views
    -0.70
    anism
    -0.68
    Episode
    -0.68
    Characters
    -0.67
    encies
    -0.67
    evidence
    -0.66
    -|
    -0.64
    POSITIVE LOGITS
     longtime
    0.94
     spokeswoman
    0.89
     spokesman
    0.87
     pseudonym
    0.86
    lder
    0.85
     lawyer
    0.84
     spokesperson
    0.84
     prominent
    0.84
     former
    0.84
     retired
    0.82
    Act Density 0.089%

    No Known Activations