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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "drop" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+
    -0.73
    EDEFAULT
    -0.72
    anthene
    -0.69
     contextLoads
    -0.64
    วย
    -0.63
    󠁢
    -0.63
    Năm
    -0.62
    {#
    -0.62
     Kita
    -0.61
     怎样
    -0.61
    POSITIVE LOGITS
     drop
    2.99
    drop
    2.83
     drops
    2.79
     Drop
    2.72
    Drop
    2.67
     DROP
    2.62
     dropping
    2.52
     Drops
    2.51
     dropped
    2.49
    drops
    2.42
    Act Density 0.035%

    No Known Activations