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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing clarity or certainty

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "obviously"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeus
    -0.80
    aily
    -0.79
    burg
    -0.77
    ament
    -0.76
    enta
    -0.73
    uality
    -0.73
    glas
    -0.72
    animous
    -0.72
    arthed
    -0.71
    enary
    -0.70
    POSITIVE LOGITS
    NULL
    0.80
     outnumbered
    0.77
     underest
    0.69
     benefited
    0.69
     infringing
    0.69
    س
    0.68
     upset
    0.68
     horr
    0.67
     belonged
    0.65
     identifiable
    0.64
    Act Density 0.046%

    No Known Activations