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

    Neuronpedia

    INDEX
    Explanations

    ranges or comparisons

    oai_token-act-pair · gpt-3.5-turbo

    complex comparisons and quantifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jen
    -0.78
    Ħ¢
    -0.67
    Ĥİ
    -0.62
     prone
    -0.61
    akov
    -0.61
     promptly
    -0.60
     Cipher
    -0.60
    POST
    -0.60
     Sites
    -0.58
    cakes
    -0.58
    POSITIVE LOGITS
     chance
    0.88
     abundance
    0.87
     overlap
    0.86
     knack
    0.86
    been
    0.85
     tendency
    0.84
     flair
    0.84
     capability
    0.82
     clout
    0.82
    chance
    0.81
    Act Density 0.459%

    No Known Activations