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

    Neuronpedia

    INDEX
    Explanations

    text related to mathematical equations and formulas

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Leban
    -0.85
     Leone
    -0.79
     Samoa
    -0.75
     Zeit
    -0.74
     Wond
    -0.73
    INGS
    -0.73
     Everyday
    -0.73
    çĭ
    -0.72
    rett
    -0.72
     fortun
    -0.72
    POSITIVE LOGITS
    correct
    0.94
    _{
    0.92
    !--
    0.91
    vert
    0.90
    interstitial
    0.88
    rm
    0.87
    perm
    0.86
    swer
    0.85
    odd
    0.85
    male
    0.85
    Act Density 0.134%

    No Known Activations