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

    Neuronpedia

    INDEX
    Explanations

    instructions or commands requesting a specific action or setting

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "specify" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ecd
    -0.77
    stra
    -0.72
    vest
    -0.72
    nih
    -0.66
    isol
    -0.66
    utsch
    -0.66
    uses
    -0.66
    luaj
    -0.66
    alog
    -0.65
    assic
    -0.65
    POSITIVE LOGITS
     parameters
    1.02
     thresholds
    1.00
     criteria
    0.97
     deadlines
    0.88
     specifications
    0.87
     rules
    0.84
     wording
    0.81
     distances
    0.81
     beforehand
    0.80
     requirements
    0.80
    Act Density 0.052%

    No Known Activations