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

    Neuronpedia

    INDEX
    Explanations

    times when the text mentions a specific month or year in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    repetitive structures or phrases within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĵĺ
    -0.73
     Pwr
    -0.71
    OST
    -0.70
    ghazi
    -0.70
    çļ
    -0.68
    icum
    -0.67
    Orderable
    -0.65
    obyl
    -0.65
    live
    -0.64
    better
    -0.63
    POSITIVE LOGITS
     vein
    0.98
     reasoning
    0.76
     article
    0.70
     scenario
    0.70
     paragraph
    0.70
     sized
    0.69
     circumstance
    0.69
     area
    0.69
     exact
    0.68
     breath
    0.66
    Act Density 0.052%

    No Known Activations