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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating likelihood or frequency

    oai_token-act-pair · gpt-3.5-turbo

    recurrent patterns indicating typicality or frequency of occurrence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    htaking
    -0.78
    atures
    -0.78
    iates
    -0.73
    jab
    -0.71
    ATS
    -0.71
    ancer
    -0.71
    chell
    -0.69
    ati
    -0.69
    elong
    -0.65
    arta
    -0.65
    POSITIVE LOGITS
    entimes
    1.17
     referred
    0.90
     accompanied
    0.89
     consist
    0.88
     overlooked
    0.85
     involve
    0.84
     encountered
    0.83
     preceded
    0.82
     vary
    0.81
     abbrevi
    0.80
    Act Density 0.182%

    No Known Activations