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

    Neuronpedia

    INDEX
    Explanations

    dialogue lines encapsulated in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks or dialogue in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pole
    -0.86
     targeted
    -0.78
     characterized
    -0.78
     predomin
    -0.73
     frontline
    -0.73
     undersc
    -0.73
     differentiated
    -0.73
     litter
    -0.72
     innov
    -0.72
     consumer
    -0.70
    POSITIVE LOGITS
    Hmm
    1.58
    Hey
    1.57
    Oh
    1.56
    Huh
    1.54
    Yeah
    1.54
    Fuck
    1.48
    Alright
    1.48
    Okay
    1.47
    Uh
    1.45
    Eh
    1.45
    Act Density 0.094%

    No Known Activations