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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names consisting of three uppercase letters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the abbreviation "GL" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riad
    -0.64
     California
    -0.62
     Dele
    -0.61
    cles
    -0.61
    Rated
    -0.61
     Hiroshima
    -0.59
    chin
    -0.59
    taining
    -0.59
    cling
    -0.59
    raviolet
    -0.59
    POSITIVE LOGITS
    ength
    1.14
    ENN
    0.89
    OSS
    0.84
    OCK
    0.82
    FW
    0.82
    ossip
    0.82
    ibrary
    0.81
    ibr
    0.81
    ASS
    0.80
    TF
    0.79
    Act Density 0.004%

    No Known Activations