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

    Neuronpedia

    INDEX
    Explanations

    specific prepositions in a sentence structure

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "at."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isphere
    -0.66
     categor
    -0.58
     solitary
    -0.57
     compe
    -0.56
     prescriptions
    -0.56
     classified
    -0.56
     mechanically
    -0.56
     protagonists
    -0.56
     straight
    -0.56
     collateral
    -0.55
    POSITIVE LOGITS
    mosp
    1.08
    las
    0.99
    onement
    0.98
    hens
    0.94
    letico
    0.88
     Subtle
    0.86
    abase
    0.85
     least
    0.85
    rial
    0.83
    mega
    0.82
    Act Density 0.052%

    No Known Activations