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

    Neuronpedia

    INDEX
    Explanations

    instances where a contrast or comparison is being made

    oai_token-act-pair · gpt-3.5-turbo

    the recurrent use of the word "while."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bed
    -0.84
    icted
    -0.79
    red
    -0.77
    ahime
    -0.74
    esi
    -0.73
    ursed
    -0.70
    uced
    -0.70
    sted
    -0.69
    bard
    -0.69
    aer
    -0.67
    POSITIVE LOGITS
     acknowledging
    1.02
     conced
    0.88
     researching
    0.85
     browsing
    0.82
     admitting
    0.81
     respecting
    0.81
     touring
    0.74
     agreeing
    0.73
     technically
    0.72
     condemning
    0.70
    Act Density 0.044%

    No Known Activations