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

    Neuronpedia

    INDEX
    Explanations

    thoughts and beliefs expressed by individuals

    oai_token-act-pair · gpt-3.5-turbo

    expressions of belief or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clock
    -0.79
    info
    -0.74
    inary
    -0.70
    aration
    -0.69
    rendered
    -0.67
    til
    -0.64
    css
    -0.64
    abi
    -0.62
    wa
    -0.62
    alia
    -0.61
    POSITIVE LOGITS
     himself
    0.70
     positives
    0.67
    olate
    0.62
    phas
    0.62
     herself
    0.61
    olated
    0.60
     passionately
    0.60
     nostalgia
    0.60
     sclerosis
    0.59
     optimism
    0.59
    Act Density 0.267%

    No Known Activations