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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values or quantities in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laus
    -0.16
    apt
    -0.16
     Harden
    -0.15
    iffe
    -0.15
    otope
    -0.15
     Levine
    -0.14
    emm
    -0.14
    ibility
    -0.14
    icy
    -0.14
    ible
    -0.14
    POSITIVE LOGITS
    felt
    0.17
    lessly
    0.16
    /th
    0.16
    islav
    0.16
    748
    0.15
    amel
    0.15
    0
    0.15
    919
    0.15
    924
    0.14
    ÅĤe
    0.14
    Act Density 0.101%

    No Known Activations