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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "chan" with varying levels of specificity

    oai_token-act-pair · gpt-3.5-turbo

    references to the online community '4chan'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ences
    -0.81
     COUR
    -0.76
    ENC
    -0.75
     Mead
    -0.67
     Ferr
    -0.65
     Jarrett
    -0.63
     Cheong
    -0.62
     Moons
    -0.62
    sson
    -0.61
     Luxem
    -0.61
    POSITIVE LOGITS
    chan
    1.17
    nel
    0.94
    esthetic
    0.90
    elist
    0.89
    bara
    0.89
    ajor
    0.87
    icum
    0.87
    thur
    0.87
    esan
    0.86
    hattan
    0.85
    Act Density 0.023%

    No Known Activations