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

    Neuronpedia

    INDEX
    Explanations

    instances where something is allowed or permitted

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "allows for."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.81
    edin
    -0.76
    hatt
    -0.72
     Originally
    -0.71
    \'
    -0.69
     Rebell
    -0.68
    itled
    -0.68
    oline
    -0.66
    weed
    -0.64
    figure
    -0.63
    POSITIVE LOGITS
     greater
    0.92
     instantaneous
    0.90
     rapid
    0.87
     simultaneous
    0.85
     mutual
    0.84
     seamless
    0.84
     elimination
    0.83
     extensive
    0.82
     gradual
    0.81
     anonymity
    0.80
    Act Density 0.105%

    No Known Activations