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

    Neuronpedia

    INDEX
    Explanations

    references to claims or assertions of rights or benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gee
    -0.16
    wich
    -0.15
    rego
    -0.15
    fly
    -0.15
    emi
    -0.15
    ially
    -0.15
    icks
    -0.14
    ialized
    -0.14
    ocks
    -0.14
    gow
    -0.14
    POSITIVE LOGITS
    ants
    0.23
    ant
    0.23
    IONS
    0.21
    acle
    0.17
    ibrated
    0.17
    aint
    0.16
    IGGER
    0.16
     Dai
    0.16
    ustering
    0.16
    fty
    0.15
    Act Density 0.025%

    No Known Activations