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

    Neuronpedia

    INDEX
    Explanations

    status indicators related to 'on' and 'off' states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undle
    -0.55
    的问道
    -0.48
     rekom
    -0.47
    ypress
    -0.47
    ValueStyle
    -0.47
    始
    -0.47
     зах
    -0.46
    onames
    -0.45
    的说道
    -0.45
     Pitman
    -0.44
    POSITIVE LOGITS
     eggs
    0.87
     egg
    0.83
     Eggs
    0.76
    Eggs
    0.75
    حوالہ
    0.67
    egg
    0.66
     beginnetje
    0.65
    eggs
    0.63
     Egg
    0.63
    Билгалдахарш
    0.62
    Act Density 0.139%

    No Known Activations