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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statistics or numerical quantities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating frequency or degree of occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö
    -0.81
    ocratic
    -0.78
    umbn
    -0.67
    ר
    -0.65
    åĤ
    -0.64
    oder
    -0.64
    ensis
    -0.64
    alian
    -0.64
    plings
    -0.64
    è¦ļéĨĴ
    -0.64
    POSITIVE LOGITS
     Stories
    0.73
    estine
    0.71
     Enough
    0.70
    entimes
    0.70
     Helpful
    0.69
    ths
    0.68
     Leader
    0.68
     Says
    0.67
     Than
    0.67
    Sounds
    0.67
    Act Density 0.019%

    No Known Activations