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

    Neuronpedia

    INDEX
    Explanations

    organizations, countries, or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations, countries, and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ..."
    -0.59
    î
    -0.57
    åĤ
    -0.54
    Enlarge
    -0.51
    SAN
    -0.50
    ``
    -0.49
    ZI
    -0.47
    odox
    -0.47
    ãģĨ
    -0.47
    chest
    -0.47
    POSITIVE LOGITS
     cannot
    0.65
     countered
    0.64
     meanwhile
    0.64
     underwent
    0.63
     reverted
    0.63
     succeeded
    0.63
     fared
    0.62
     retains
    0.61
     lacks
    0.60
     also
    0.60
    Act Density 1.060%

    No Known Activations