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

    Neuronpedia

    INDEX
    Explanations

    quotes or direct speech in the form of a conversation

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks used in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pole
    -0.85
     adjud
    -0.78
     valued
    -0.76
     characterized
    -0.75
     accident
    -0.74
     seasoned
    -0.73
     targeted
    -0.73
     foreseeable
    -0.73
     innov
    -0.73
     previously
    -0.72
    POSITIVE LOGITS
    Yeah
    1.81
    Oh
    1.70
    Huh
    1.70
    Hmm
    1.67
    Uh
    1.67
    Yes
    1.65
    Alright
    1.64
    Okay
    1.64
    Hey
    1.63
    Fuck
    1.57
    Act Density 0.101%

    No Known Activations