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

    Neuronpedia

    INDEX
    Explanations

    mention of flat things or the word "flat" with varying intensity

    oai_token-act-pair · gpt-3.5-turbo

    references to flatness or the term "flat" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IVERS
    -0.77
    utra
    -0.75
     warr
    -0.74
     ANGEL
    -0.74
     appropri
    -0.72
    GBT
    -0.71
    EMENT
    -0.70
    ymes
    -0.68
    EStream
    -0.68
    REDACTED
    -0.62
    POSITIVE LOGITS
    ulence
    1.47
    ulent
    1.37
    tered
    1.36
    iron
    1.20
    bread
    1.16
    bed
    1.14
    lining
    1.12
    bush
    1.09
    ters
    1.07
    tering
    1.02
    Act Density 0.036%

    No Known Activations