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

    Neuronpedia

    INDEX
    Explanations

    the recurring use of the word "although."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    contrasting information or exceptions within a sentence or paragraph

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    hal
    -0.78
    Eye
    -0.76
    lees
    -0.76
    isible
    -0.75
    enter
    -0.74
    elle
    -0.73
    ais
    -0.72
    aed
    -0.69
    ath
    -0.68
    edu
    -0.67
    POSITIVE LOGITS
    soever
    0.82
     acknowledging
    0.82
     retaining
    0.77
     conced
    0.76
     agreeing
    0.75
    chery
    0.71
     browsing
    0.70
     recogn
    0.70
     compiling
    0.70
     dating
    0.69
    Act Density 0.022%

    No Known Activations