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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "even" is used

    oai_token-act-pair · gpt-3.5-turbo

    the word "even" and its repeated use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rend
    -0.83
    aim
    -0.72
    hammad
    -0.71
    unity
    -0.71
    ========
    -0.71
    ruby
    -0.68
    advertising
    -0.67
    ugal
    -0.67
    actly
    -0.66
    arry
    -0.66
    POSITIVE LOGITS
     remotely
    0.98
    handedly
    0.96
     though
    0.91
     tho
    0.87
     joked
    0.81
    handed
    0.81
     hinted
    0.77
     worse
    0.76
     entertained
    0.74
     managed
    0.73
    Act Density 0.060%

    No Known Activations