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

    Neuronpedia

    INDEX
    Explanations

    pairs of entities that are being compared or contrasted

    oai_token-act-pair · gpt-3.5-turbo

    instances of subjects being linked with actions or states of being, particularly in a comparative or relational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Newsletter
    -0.84
    undo
    -0.72
    lamm
    -0.69
    ogle
    -0.69
     Collider
    -0.64
    mud
    -0.62
    Order
    -0.61
    atown
    -0.61
    metadata
    -0.60
    order
    -0.60
    POSITIVE LOGITS
     halves
    0.94
     equally
    0.90
     sexes
    0.85
     together
    0.82
     simultaneously
    0.82
    aughed
    0.79
     sides
    0.79
     alike
    0.77
     identical
    0.76
     respective
    0.76
    Act Density 0.224%

    No Known Activations