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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing strong agreement or endorsement

    oai_token-act-pair · gpt-3.5-turbo

    expressions of certainty or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ently
    -0.80
    sembly
    -0.80
    roups
    -0.78
     Mour
    -0.77
     moreover
    -0.69
    acity
    -0.69
    aciously
    -0.68
    soever
    -0.67
    entary
    -0.67
     Simulator
    -0.67
    POSITIVE LOGITS
     gonna
    0.75
     recommend
    0.72
     wanna
    0.72
     gotta
    0.69
     got
    0.69
     underrated
    0.65
     NOT
    0.63
     uptick
    0.63
     qualifies
    0.62
     correlated
    0.62
    Act Density 0.046%

    No Known Activations