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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical locations and individuals associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istically
    -0.95
    istic
    -0.92
    isting
    -0.91
    istics
    -0.90
    ists
    -0.87
    arians
    -0.86
    aries
    -0.85
    reads
    -0.84
    ist
    -0.81
    ism
    -0.81
    POSITIVE LOGITS
    NetMessage
    0.89
    ĺħ
    0.81
     cumbers
    0.76
     externalToEVAOnly
    0.75
    hammad
    0.75
     teasp
    0.74
    EStream
    0.73
    asus
    0.73
    cules
    0.71
    rals
    0.71
    Act Density 0.096%

    No Known Activations