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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "surprising" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VolleyError
    -0.51
    VYMaps
    -0.48
    RTDA
    -0.46
    twimg
    -0.45
    shl
    -0.44
     Roskov
    -0.43
     препратки
    -0.43
    +#+#
    -0.42
    ammans
    -0.41
    ̈́
    -0.40
    POSITIVE LOGITS
     surprisingly
    0.87
     Surprisingly
    0.69
    意外と
    0.69
    居然
    0.68
    Surprisingly
    0.67
    竟
    0.60
     unexpectedly
    0.59
    竟然
    0.59
     oddly
    0.58
    prisingly
    0.57
    Act Density 0.454%

    No Known Activations