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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a presence of evidence or legitimate claims in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -0.79
     Jefus
    -0.78
     chofe
    -0.75
     myſelf
    -0.75
     Monfieur
    -0.73
     pleaſure
    -0.70
     Etr
    -0.70
     Shakspeare
    -0.69
     uſe
    -0.69
    ]-->
    -0.69
    POSITIVE LOGITS
    ://
    0.54
    ineno
    0.49
     "
    0.48
    ########.
    0.47
    FormTagHelper
    0.47
    lapsingToolbar
    0.46
    iling
    0.46
    ি
    0.46
    enumi
    0.46
     čin
    0.45
    Act Density 0.299%

    No Known Activations