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

    Neuronpedia

    INDEX
    Explanations

    phrases related to verbal communication or expressions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ded
    -0.78
    schild
    -0.76
    oday
    -0.75
    ithmetic
    -0.68
    icipated
    -0.67
    kus
    -0.66
     Stores
    -0.66
     inaction
    -0.66
     ESA
    -0.66
    rals
    -0.65
    POSITIVE LOGITS
     tongues
    0.94
     tongue
    0.91
     fry
    0.79
    bone
    0.79
    mith
    0.78
     Tong
    0.77
    ice
    0.75
     protr
    0.75
    gently
    0.74
     muc
    0.74
    Act Density 0.034%

    No Known Activations