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

    Neuronpedia

    INDEX
    Explanations

    references to specific organizations, events, and titles

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations, institutions, and their roles or areas of focus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unfocusedRange
    -0.66
    afety
    -0.63
    PF
    -0.60
    gaard
    -0.58
     sqor
    -0.57
    tro
    -0.56
    vik
    -0.55
    twitch
    -0.54
    inelli
    -0.54
     silence
    -0.54
    POSITIVE LOGITS
     Cain
    0.60
    ר
    0.56
    thinkable
    0.54
     Conan
    0.53
     millenn
    0.53
     Migration
    0.53
    chains
    0.53
    ļéĨĴ
    0.52
     Hail
    0.51
    nant
    0.49
    Act Density 1.121%

    No Known Activations