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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparison using the word "Like"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "like" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ape
    -0.82
    ennes
    -0.81
    duction
    -0.79
    Americ
    -0.77
    ALE
    -0.77
     enthusi
    -0.77
    duct
    -0.76
    dies
    -0.75
    aley
    -0.72
    tein
    -0.71
    POSITIVE LOGITS
    lihood
    1.74
    liest
    1.25
    lier
    1.13
    liness
    0.85
    minded
    0.82
     clock
    0.77
    ly
    0.76
     drafts
    0.69
     minded
    0.66
     Mothers
    0.66
    Act Density 0.035%

    No Known Activations