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

    Neuronpedia

    INDEX
    Explanations

    phrases related to highlighting importance or uniqueness

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the significance or magnitude of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Airl
    -0.71
     Annotations
    -0.70
     RCMP
    -0.69
     Scully
    -0.65
     McKenzie
    -0.64
    ysc
    -0.63
    Explore
    -0.63
     Uriel
    -0.63
    np
    -0.62
     Inspector
    -0.62
    POSITIVE LOGITS
     thing
    1.05
     feat
    0.82
     scenario
    0.80
    uncture
    0.79
     situation
    0.76
     device
    0.76
     delicate
    0.76
    sembly
    0.75
     hypothetical
    0.74
     circumstance
    0.74
    Act Density 0.032%

    No Known Activations