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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing absurdity or ridiculousness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Manip
    -0.38
     Incl
    -0.35
     neutral
    -0.34
    relu
    -0.33
     manip
    -0.33
     noDo
    -0.33
    neutral
    -0.32
     insuffisamment
    -0.32
     keenly
    -0.32
    manip
    -0.32
    POSITIVE LOGITS
     absurdity
    0.94
     absurd
    0.88
     ridiculous
    0.88
     absur
    0.84
     crazy
    0.84
    posterous
    0.84
     bizarre
    0.81
     locura
    0.81
     craz
    0.79
     madness
    0.78
    Act Density 0.471%

    No Known Activations