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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations followed by actions or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases or references to dangerous situations or dramatic events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utical
    -0.66
     dissu
    -0.62
     Blink
    -0.57
    iton
    -0.57
     Bloom
    -0.56
     Trog
    -0.55
     Squadron
    -0.54
     intending
    -0.54
     hopping
    -0.54
    hement
    -0.53
    POSITIVE LOGITS
    ³³³³
    1.19
    ³³³³³³³³³³³³³³³³
    1.11
    ³³³³³³³³
    1.10
    ³³³
    1.07
    ³³
    0.86
    SPONSORED
    0.74
    rawdownloadcloneembedreportprint
    0.68
    arta
    0.66
    sonian
    0.65
    Posted
    0.65
    Act Density 0.701%

    No Known Activations