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

    Neuronpedia

    INDEX
    Explanations

    references to specific terms or phrases containing the abbreviation "CH."

    oai_token-act-pair · gpt-3.5-turbo

    references to the abbreviation "CH" as it appears in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ged
    -0.65
     favour
    -0.64
     Yor
    -0.61
     favor
    -0.61
     proportions
    -0.61
    glass
    -0.59
    gaard
    -0.58
    ned
    -0.58
     redu
    -0.57
     onward
    -0.55
    POSITIVE LOGITS
    APTER
    1.39
    ECK
    1.31
    ILD
    1.24
    AIR
    1.23
    ANGE
    1.20
    AIN
    1.20
    INA
    1.15
    OOL
    1.15
    IPS
    1.14
    ANN
    1.13
    Act Density 0.015%

    No Known Activations