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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or groups involved in significant events or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Niet
    -0.64
     Noon
    -0.53
     Vaugh
    -0.51
     undermin
    -0.50
     predec
    -0.49
     antid
    -0.47
     Shining
    -0.47
     [*
    -0.47
    vertising
    -0.46
    Flow
    -0.46
    POSITIVE LOGITS
     ):
    0.53
     Belfast
    0.51
    photos
    0.51
    ↵
    0.50
     RELEASE
    0.49
     sqor
    0.49
     chars
    0.49
     Xperia
    0.48
    soType
    0.45
    !!!!
    0.45
    Act Density 1.240%

    No Known Activations