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

    Neuronpedia

    INDEX
    Explanations

    instances of removal or dismissal from positions or titles

    oai_token-act-pair · gpt-3.5-turbo

    instances of removal or resignation from positions or offices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ghost
    -0.74
    Enlarge
    -0.73
    sylv
    -0.70
    aeus
    -0.69
    rien
    -0.65
    culosis
    -0.64
     sucker
    -0.64
    uzzle
    -0.64
    iour
    -0.63
    reset
    -0.63
    POSITIVE LOGITS
     consideration
    1.02
     existence
    0.91
     contention
    0.87
     duty
    0.79
     orbit
    0.77
     eligibility
    0.76
     circulation
    0.76
     participating
    0.76
     sight
    0.76
     bounds
    0.75
    Act Density 0.115%

    No Known Activations