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

    Neuronpedia

    INDEX
    Explanations

    words related to educational institutions and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.77
    BibitemShut
    -1.73
     purpoſe
    -1.65
     pleaſure
    -1.59
     themſelves
    -1.58
     itſelf
    -1.56
    ſelf
    -1.55
     ―――――
    -1.55
    ſelves
    -1.49
     ſeveral
    -1.48
    POSITIVE LOGITS
    il
    0.84
    z
    0.83
    j
    0.81
    K
    0.80
    al
    0.80
    er
    0.78
    N
    0.77
    ch
    0.77
    b
    0.77
    ul
    0.76
    Act Density 2.435%

    No Known Activations