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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing casual exclamations or interruptions

    oai_token-act-pair · gpt-3.5-turbo

    conversational phrases and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IRE
    -0.69
    ãĤ·ãĥ£
    -0.68
    obook
    -0.67
    MpServer
    -0.66
    Hart
    -0.65
    ario
    -0.64
    arians
    -0.64
    MRI
    -0.64
    UGC
    -0.63
    aria
    -0.63
    POSITIVE LOGITS
     uh
    0.83
     yeah
    0.72
     tease
    0.71
     wow
    0.71
    othing
    0.68
     hi
    0.67
     whisper
    0.66
    ombies
    0.65
     crap
    0.65
     u
    0.64
    Act Density 0.041%

    No Known Activations