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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the need for action or change

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a call to action or urgency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ournal
    -0.81
    iership
    -0.77
    insula
    -0.77
    ourt
    -0.74
    riad
    -0.74
    hemat
    -0.71
    agonist
    -0.69
    utsu
    -0.69
     perpend
    -0.68
    onut
    -0.68
    POSITIVE LOGITS
     consuming
    0.76
     anew
    0.74
    llor
    0.72
    ful
    0.71
     recons
    0.68
    fully
    0.65
     overdue
    0.64
    ward
    0.63
    bringer
    0.61
     Spiral
    0.60
    Act Density 0.028%

    No Known Activations