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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "even" is used in text

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases indicating "even" to emphasize the extraordinary nature of the situations described

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rend
    -0.91
     Needs
    -0.60
     mayhem
    -0.60
    aim
    -0.60
     Bash
    -0.59
    cent
    -0.58
    Exit
    -0.58
     bearings
    -0.58
    unity
    -0.57
    cel
    -0.57
    POSITIVE LOGITS
     remotely
    0.90
    ivari
    0.80
     indirectly
    0.77
    handedly
    0.75
     though
    0.75
    handed
    0.73
     tho
    0.73
    swick
    0.73
    mont
    0.69
    £ı
    0.69
    Act Density 0.062%

    No Known Activations