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

    Neuronpedia

    INDEX
    Explanations

    skeletal-related terms or references

    oai_token-act-pair · gpt-3.5-turbo

    terms related to skeletons and skeletal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fw
    -0.75
    nor
    -0.73
     Synd
    -0.70
    ner
    -0.70
    ional
    -0.69
    nar
    -0.68
    words
    -0.65
     Sector
    -0.64
    itsch
    -0.64
     Wim
    -0.64
    POSITIVE LOGITS
    letal
    0.99
     Ske
    0.87
    atures
    0.83
    reditary
    0.81
    leton
    0.80
    reen
    0.79
    pta
    0.78
    jriwal
    0.77
     Flavoring
    0.76
    cano
    0.75
    Act Density 0.037%

    No Known Activations