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

    Neuronpedia

    INDEX
    Explanations

    the word "one" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nya
    -0.14
    hurst
    -0.14
    nar
    -0.14
    l
    -0.14
    reh
    -0.14
    ãĥ¼ãĥĭ
    -0.14
    aceous
    -0.14
    elerden
    -0.14
    211
    -0.13
    UBL
    -0.13
    POSITIVE LOGITS
     of
    0.17
    -click
    0.16
    SELF
    0.15
    verity
    0.15
    onde
    0.15
    onta
    0.15
     Cov
    0.14
    lettes
    0.14
    naments
    0.14
    -direction
    0.14
    Act Density 0.127%

    No Known Activations