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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical details and procedures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leground
    -0.61
     overseen
    -0.60
    ingly
    -0.59
     among
    -0.59
    thood
    -0.58
     based
    -0.57
     spearheaded
    -0.56
    ornings
    -0.56
    linked
    -0.56
     thereby
    -0.55
    POSITIVE LOGITS
     slightest
    1.09
     latter
    1.05
     remainder
    1.04
     entire
    1.02
     same
    1.01
     entirety
    0.99
     aforementioned
    0.98
    ses
    0.95
     smallest
    0.95
     whole
    0.92
    Act Density 1.224%

    No Known Activations