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

    Neuronpedia

    INDEX
    Explanations

    phrases that continue a conversation or narrative

    oai_token-act-pair · gpt-3.5-turbo

    the conjunctions "and" and "," indicating connections or additions in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.96
    Born
    -0.81
    unts
    -0.76
    rises
    -0.76
    Contents
    -0.75
    isible
    -0.73
    âĻ¥
    -0.71
    icult
    -0.69
    tnc
    -0.68
    phant
    -0.67
    POSITIVE LOGITS
     then
    1.08
     subsequently
    1.01
     promptly
    0.99
     secondly
    0.98
     proceeded
    0.97
     consequently
    0.94
     thereafter
    0.92
     moreover
    0.91
     prest
    0.89
     thence
    0.89
    Act Density 0.355%

    No Known Activations