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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discovering new information or items

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to discovering or coming across information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.75
    mort
    -0.75
    cussion
    -0.72
    etary
    -0.71
    ))))
    -0.69
    ŃĶ
    -0.67
    cise
    -0.67
    venge
    -0.66
    wake
    -0.66
    VP
    -0.65
    POSITIVE LOGITS
     something
    0.83
     objectionable
    0.81
     suspicious
    0.79
     irregularities
    0.79
     clues
    0.77
     inconsistencies
    0.77
     glimps
    0.76
     discrepancies
    0.74
     interesting
    0.73
     similarities
    0.73
    Act Density 0.162%

    No Known Activations