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

    Neuronpedia

    INDEX
    Explanations

    negatively framed or critical comments

    oai_token-act-pair · gpt-3.5-turbo

    negative assessments of experiences or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GEAR
    -0.82
     Versus
    -0.76
     Reloaded
    -0.69
     File
    -0.67
     Rivals
    -0.66
     induction
    -0.66
     Downing
    -0.66
     Theft
    -0.66
     Pieces
    -0.66
     Caller
    -0.65
    POSITIVE LOGITS
    famous
    1.35
    existent
    1.32
    great
    1.25
    named
    1.22
    popular
    1.21
    educated
    1.20
    successful
    1.20
    powerful
    1.19
    biased
    1.19
    expensive
    1.18
    Act Density 0.035%

    No Known Activations