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

    Neuronpedia

    INDEX
    Explanations

    references to code-related terms and implementation details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    代
    -0.18
    itte
    -0.15
    icum
    -0.15
    ücken
    -0.15
    RAINT
    -0.14
    ender
    -0.14
     Falling
    -0.14
    aby
    -0.14
    hs
    -0.14
    rah
    -0.13
    POSITIVE LOGITS
    upal
    0.19
    laces
    0.16
    .bb
    0.14
    830
    0.14
    rop
    0.14
    onym
    0.14
    eson
    0.14
     Shotgun
    0.14
    icens
    0.13
     Ferd
    0.13
    Act Density 0.003%

    No Known Activations