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

    Neuronpedia

    INDEX
    Explanations

    phrases related to success or performance evaluation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to someone's historical performance or credibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essel
    -0.87
    edi
    -0.78
    sub
    -0.75
    ishable
    -0.73
     uncond
    -0.73
    hap
    -0.73
    andr
    -0.71
    tein
    -0.70
    amaz
    -0.70
    adin
    -0.70
    POSITIVE LOGITS
     record
    0.81
     breaker
    0.79
    record
    0.68
     recorder
    0.68
     Record
    0.67
     holder
    0.67
    olester
    0.66
     achievement
    0.65
     Choice
    0.64
     achievements
    0.63
    Act Density 0.035%

    No Known Activations