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

    Neuronpedia

    INDEX
    Explanations

    sentences that express suggestions, suggestions, or requests for action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     raiſ
    -0.60
    WaitGroup
    -0.59
     Cæsar
    -0.54
     Shakspeare
    -0.53
     isNameExpr
    -0.53
     Albin
    -0.52
     chofe
    -0.52
     againſt
    -0.52
     intellect
    -0.51
     uſed
    -0.50
    POSITIVE LOGITS
    httphttps
    0.70
    Rujuakan
    0.61
    帖最后由
    0.58
     Chwiliwch
    0.57
    //
    0.53
    istisches
    0.49
    سطس
    0.49
    AndEndTag
    0.49
     erstmals
    0.48
    ///</
    0.47
    Act Density 0.314%

    No Known Activations