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

    Neuronpedia

    INDEX
    Explanations

    terms related to hydrogen and its chemical properties or uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.17
    inue
    -0.16
    ibling
    -0.16
     Harm
    -0.15
    ÅĻiv
    -0.15
    pz
    -0.14
    rouw
    -0.14
    ãĥ¼ãĥ¬
    -0.14
    коз
    -0.14
     Harr
    -0.14
    POSITIVE LOGITS
    carbon
    0.32
    xy
    0.30
    electric
    0.29
    dynamic
    0.28
    thermal
    0.28
    chlor
    0.28
    gens
    0.28
    pon
    0.26
    gel
    0.26
    phil
    0.26
    Act Density 0.013%

    No Known Activations