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

    Neuronpedia

    INDEX
    Explanations

    dialogue lines

    oai_token-act-pair · gpt-3.5-turbo

    dialogue or expressions of personal feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.81
     satell
    -0.70
    kefeller
    -0.68
     exported
    -0.68
     Newark
    -0.67
    ewitness
    -0.63
     leased
    -0.63
     looted
    -0.62
     Tel
    -0.61
     dubbed
    -0.61
    POSITIVE LOGITS
    âĢ
    1.25
     âĢ
    0.99
     honestly
    0.89
     Honestly
    0.84
    Honestly
    0.82
     I
    0.82
    âĻ
    0.80
    ··
    0.80
     âĶ
    0.79
     âĿ
    0.78
    Act Density 0.572%

    No Known Activations