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

    Neuronpedia

    INDEX
    Explanations

    comparisons using "like"

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that imply resemblance or similarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ô
    -0.80
    atel
    -0.80
    ifi
    -0.75
    achus
    -0.73
    restling
    -0.73
    atech
    -0.72
    udeb
    -0.71
    UNCH
    -0.70
    arians
    -0.70
    earch
    -0.68
    POSITIVE LOGITS
    lihood
    2.18
     tendencies
    1.04
    liest
    1.02
    liness
    0.97
     qualities
    0.91
    minded
    0.88
     structures
    0.87
    lier
    0.87
     sentiments
    0.84
     consistency
    0.84
    Act Density 0.029%

    No Known Activations