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

    Neuronpedia

    INDEX
    Explanations

    quantifiers related to time intervals

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "another" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isters
    -0.82
    olas
    -0.76
    eers
    -0.73
    hips
    -0.73
    bows
    -0.72
    ooks
    -0.71
    alties
    -0.69
    folios
    -0.69
    also
    -0.68
    orig
    -0.68
    POSITIVE LOGITS
    worldly
    1.22
     dimension
    1.07
     installment
    0.95
     avenue
    0.94
     notch
    0.94
     layer
    0.89
     decade
    0.88
     round
    0.85
     batch
    0.85
     iteration
    0.80
    Act Density 0.071%

    No Known Activations