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

    Neuronpedia

    INDEX
    Explanations

    phrases beginning with the word "comes."

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "comes" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ricular
    -0.97
    icon
    -0.92
    raid
    -0.82
    cos
    -0.82
    ²¾
    -0.81
    cell
    -0.81
    icons
    -0.79
    sav
    -0.79
    olor
    -0.79
    illusion
    -0.76
    POSITIVE LOGITS
     undone
    1.00
     WRITE
    0.88
     ashore
    0.79
     Nieto
    0.75
     Steele
    0.74
     forward
    0.73
     forth
    0.73
     out
    0.72
     OUT
    0.71
     Cipher
    0.71
    Act Density 0.038%

    No Known Activations