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

    Neuronpedia

    INDEX
    Explanations

    words related to human face or facial features

    oai_token-act-pair · gpt-3.5-turbo

    the word "fac" and its variations, indicating a focus on facial features or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    went
    -0.72
    ettle
    -0.68
     Pole
    -0.67
    oshi
    -0.67
    itter
    -0.65
     Orion
    -0.64
    usha
    -0.63
     Nib
    -0.63
    linux
    -0.61
    adder
    -0.61
    POSITIVE LOGITS
     fac
    3.86
     Fac
    2.39
    fac
    2.21
    Fac
    2.13
     facade
    1.36
     FAC
    1.34
     facial
    1.17
     fa
    1.15
     voic
    1.10
     facilit
    1.07
    Act Density 0.018%

    No Known Activations