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

    Neuronpedia

    INDEX
    Explanations

    the past tense verb "shed"

    oai_token-act-pair · gpt-3.5-turbo

    the word "hed" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     train
    -0.64
     Mi
    -0.59
     incumbent
    -0.58
     defeat
    -0.58
     mistake
    -0.57
     trains
    -0.57
     study
    -0.56
     visit
    -0.56
     mastering
    -0.55
     mL
    -0.54
    POSITIVE LOGITS
    hed
    4.97
    hing
    2.49
    hes
    2.23
    hedral
    2.00
    hest
    1.79
    hers
    1.69
    hedon
    1.57
    hend
    1.55
    her
    1.54
    hen
    1.53
    Act Density 0.010%

    No Known Activations