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

    Neuronpedia

    INDEX
    Explanations

    instances of realization or self-discovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ect
    -0.18
    ÏĦÏĥι
    -0.17
    duk
    -0.15
    lein
    -0.15
    REEN
    -0.15
    shal
    -0.14
     krát
    -0.14
     actionTypes
    -0.13
    Helpers
    -0.13
     é©
    -0.13
    POSITIVE LOGITS
    inalg
    0.17
     indeed
    0.17
    heck
    0.15
     actually
    0.15
    æĺ¯æĪij
    0.14
    irit
    0.14
    uron
    0.14
     ga
    0.14
     Sandbox
    0.14
    IDGET
    0.14
    Act Density 0.166%

    No Known Activations