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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that begin with "if."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.97
    ſelves
    -0.87
     للمعارف
    -0.85
     itſelf
    -0.84
     houſe
    -0.84
     ſeveral
    -0.83
     Reſ
    -0.83
     Monfieur
    -0.83
     صوتيه
    -0.82
     himſelf
    -0.81
    POSITIVE LOGITS
     anything
    0.99
     anyone
    0.89
     you
    0.87
     ever
    0.85
     it
    0.76
     nothing
    0.73
     only
    0.72
     indeed
    0.72
     anybody
    0.70
     any
    0.69
    Act Density 0.103%

    No Known Activations