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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that suggest irrationality or eccentricity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    naphthal
    -0.66
    gypti
    -0.64
     bedient
    -0.64
    Quel
    -0.64
    帖最后由
    -0.63
    EntityFramework
    -0.62
    dehydes
    -0.61
    warna
    -0.61
    ائص
    -0.61
    فحة
    -0.61
    POSITIVE LOGITS
     insane
    1.09
     silly
    1.08
     crazy
    1.07
     stupid
    1.00
     Silly
    1.00
     madness
    0.99
    Crazy
    0.99
     foolish
    0.99
     absurd
    0.98
     ridiculous
    0.97
    Act Density 0.211%

    No Known Activations