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

    Neuronpedia

    INDEX
    Explanations

    comparisons using the word "like"

    oai_token-act-pair · gpt-3.5-turbo

    expressions that denote comparison or similarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MED
    -0.82
    achus
    -0.73
    icians
    -0.73
    yna
    -0.72
    kins
    -0.72
    aver
    -0.71
    udeb
    -0.70
    rad
    -0.69
    Ô
    -0.68
    Sports
    -0.68
    POSITIVE LOGITS
    lihood
    2.21
     tendencies
    1.03
     structure
    0.99
     structures
    0.98
     qualities
    0.98
     atmosphere
    0.93
    liest
    0.92
     substance
    0.89
    liness
    0.88
     creature
    0.87
    Act Density 0.044%

    No Known Activations