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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a range or interval

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "between" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iasis
    -0.74
    der
    -0.74
    vous
    -0.74
    herty
    -0.73
    bi
    -0.72
    OGR
    -0.71
    Lev
    -0.71
    elman
    -0.69
    rav
    -0.69
    di
    -0.69
    POSITIVE LOGITS
    between
    0.77
     halves
    0.68
    ween
    0.67
     between
    0.66
     friendships
    0.66
     sexes
    0.64
     rounds
    0.62
     Between
    0.61
     genders
    0.61
     buddies
    0.60
    Act Density 0.049%

    No Known Activations