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

    Neuronpedia

    INDEX
    Explanations

    people's names

    oai_token-act-pair · gpt-3.5-turbo

    names or references to specific individuals, particularly those with the prefix "Har."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     subp
    -0.70
    İĭ
    -0.69
     acron
    -0.67
     carrot
    -0.65
     guarant
    -0.63
     contrace
    -0.63
     magnification
    -0.62
    ©¶æ
    -0.61
     isot
    -0.60
    ifice
    -0.59
    POSITIVE LOGITS
    schild
    0.79
    raid
    0.75
    inton
    0.73
    inger
    0.71
    ette
    0.70
    idays
    0.67
    ã
    0.67
    unning
    0.67
    dal
    0.66
    SHA
    0.66
    Act Density 0.122%

    No Known Activations