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

    Neuronpedia

    INDEX
    Explanations

    words or phrases composed mostly of consonants

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    andestine
    -0.47
    ments
    -0.46
     flask
    -0.46
    hirt
    -0.46
     Kinnikuman
    -0.46
    eus
    -0.45
    mpeg
    -0.45
    mented
    -0.45
     penetration
    -0.43
    hematic
    -0.43
    POSITIVE LOGITS
    ICLE
    0.77
    icular
    0.63
    uty
    0.55
    earch
    0.47
    orse
    0.47
    TAG
    0.46
    BLE
    0.46
    iHUD
    0.45
    OY
    0.45
    FI
    0.45
    Act Density 0.111%

    No Known Activations