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

    Neuronpedia

    INDEX
    Explanations

    words related to time and progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating persistence or ongoing situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    attery
    -0.76
    erity
    -0.74
    ĪĴ
    -0.68
    cffff
    -0.66
     istg
    -0.65
    £ı
    -0.64
     Mortgage
    -0.64
    ospace
    -0.63
    Reporting
    -0.62
    Tesla
    -0.62
    POSITIVE LOGITS
     unanswered
    0.79
     adolesc
    0.76
     scratching
    0.75
     untouched
    0.72
    ipop
    0.71
     intact
    0.70
     unsolved
    0.70
    awed
    0.69
     unresolved
    0.67
    birth
    0.66
    Act Density 0.279%

    No Known Activations