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

    Neuronpedia

    INDEX
    Explanations

    words related to locations or people named "Seab"

    oai_token-act-pair · gpt-3.5-turbo

    sequences of letters that often represent the endings of words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pigs
    -0.68
    »Ĵ
    -0.63
    ij士
    -0.60
     Lovely
    -0.59
     Palest
    -0.58
     innocence
    -0.58
     CLICK
    -0.57
    é¾
    -0.57
     clicked
    -0.56
    ãĤ¤ãĥĪ
    -0.56
    POSITIVE LOGITS
    aults
    0.84
    ember
    0.74
    ecast
    0.73
    uku
    0.71
    arth
    0.71
    eper
    0.71
    ault
    0.69
    irm
    0.68
    rets
    0.68
    ologne
    0.67
    Act Density 0.091%

    No Known Activations