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

    Neuronpedia

    INDEX
    Explanations

    sharp and intense language or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sharpness or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uthor
    -0.78
    YL
    -0.76
     Alive
    -0.76
    FORE
    -0.75
    pty
    -0.74
    ORED
    -0.71
    isSpecialOrderable
    -0.67
    reon
    -0.66
     Leia
    -0.65
    repeat
    -0.64
    POSITIVE LOGITS
    ened
    1.29
    ening
    1.22
    ener
    1.07
    ness
    1.04
    est
    1.00
    eness
    0.87
    edo
    0.86
     arrow
    0.84
     blade
    0.82
    eners
    0.81
    Act Density 0.033%

    No Known Activations