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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "had" and variations of past tense or possessive experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſtre
    -0.50
     houſe
    -0.50
     preſent
    -0.47
     perſon
    -0.46
    wiſe
    -0.45
    (__
    -0.44
     worshi
    -0.43
    blume
    -0.42
     purpoſe
    -0.42
    arrón
    -0.42
    POSITIVE LOGITS
     Had
    0.86
    Had
    0.85
     Hadid
    0.78
    had
    0.77
     had
    0.77
     Hadley
    0.76
     HAD
    0.71
    did
    0.71
    Hed
    0.68
    HAD
    0.67
    Act Density 0.166%

    No Known Activations