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

    Neuronpedia

    INDEX
    Explanations

    words related to legal or criminal situations

    oai_token-act-pair · gpt-3.5-turbo

    details related to critical conditions and medical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     referen
    -0.54
    illions
    -0.53
    arsity
    -0.53
     scrut
    -0.51
     predec
    -0.49
    aida
    -0.48
    etheus
    -0.48
    acebook
    -0.47
    efe
    -0.47
    querade
    -0.47
    POSITIVE LOGITS
     âĵĺ
    0.58
     Dism
    0.53
    pmwiki
    0.53
    .--
    0.52
     Phant
    0.50
    SourceFile
    0.49
     AST
    0.48
    ymes
    0.48
     Fract
    0.48
     Redux
    0.47
    Act Density 3.166%

    No Known Activations