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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to sharp objects or qualities

    oai_token-act-pair · gpt-3.5-turbo

    the word "sharp" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uthor
    -0.78
    pty
    -0.76
    YL
    -0.75
    FORE
    -0.73
     Alive
    -0.73
    8000
    -0.72
    BLE
    -0.71
    ORED
    -0.69
    osponsors
    -0.69
    ICAN
    -0.68
    POSITIVE LOGITS
    ened
    1.27
    ening
    1.17
    ener
    1.06
    ness
    0.99
    est
    0.94
     arrow
    0.87
     strokes
    0.86
    edo
    0.85
     elbows
    0.84
     edges
    0.83
    Act Density 0.024%

    No Known Activations