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

    Neuronpedia

    INDEX
    Explanations

    references to alternative options or choices

    oai_token-act-pair · gpt-3.5-turbo

    terms related to alternatives and alternative perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    older
    -0.90
    oho
    -0.71
    gaard
    -0.70
    reditary
    -0.68
    owler
    -0.67
    iencies
    -0.66
     Bees
    -0.65
    midt
    -0.64
    cedented
    -0.64
    hips
    -0.63
    POSITIVE LOGITS
     lifestyles
    1.08
     viewpoints
    1.02
     explanations
    0.92
     viewpoint
    0.89
     routes
    0.86
     universes
    0.83
     modes
    0.82
     interpretations
    0.82
     route
    0.81
     perspectives
    0.81
    Act Density 0.048%

    No Known Activations