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

    Neuronpedia

    INDEX
    Explanations

    references to the term "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.88
    UIControlState
    -0.83
    ########.
    -0.83
    <>("
    -0.80
     Völ
    -0.80
    TProtocol
    -0.79
     beginnetje
    -0.76
     McGovern
    -0.76
    Portale
    -0.75
     uska
    -0.75
    POSITIVE LOGITS
     oneself
    0.78
     myself
    0.73
     Myself
    0.73
     herself
    0.71
     selves
    0.71
    myself
    0.67
     yourself
    0.66
     Yourself
    0.65
    Myself
    0.65
     ourselves
    0.65
    Act Density 0.024%

    No Known Activations