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

    Neuronpedia

    INDEX
    Explanations

    references to amounts of money or financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to academic performance or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     :(
    -0.74
     didnt
    -0.68
     *)
    -0.67
     NZ
    -0.66
     doesnt
    -0.64
     english
    -0.64
     dont
    -0.63
     Cancel
    -0.60
     Reply
    -0.59
     ;)
    -0.58
    POSITIVE LOGITS
    oward
    0.71
    asuring
    0.62
    Thumbnail
    0.61
    ocative
    0.59
    raphic
    0.57
    ophysical
    0.56
    conom
    0.56
     potentially
    0.54
    ãģĨ
    0.54
    icipated
    0.54
    Act Density 1.256%

    No Known Activations