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

    Neuronpedia

    INDEX
    Explanations

    occurrences of attribute names in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    μοί
    -0.15
    ande
    -0.15
    092
    -0.15
    ombs
    -0.15
     Boeh
    -0.15
    plorer
    -0.14
     festivals
    -0.14
    á»ĵn
    -0.14
    oeff
    -0.14
    rias
    -0.14
    POSITIVE LOGITS
    erchant
    0.15
    adows
    0.15
    appers
    0.14
     Punch
    0.14
     Dis
    0.14
     Tribune
    0.14
     âĹĦ
    0.14
    urette
    0.13
    Tmp
    0.13
    linger
    0.13
    Act Density 0.004%

    No Known Activations