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

    Neuronpedia

    INDEX
    Explanations

    references to humor and comedic elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    855
    -0.18
    chl
    -0.16
    ivr
    -0.15
    enie
    -0.15
    Ïĥι
    -0.15
    547
    -0.15
    854
    -0.14
    nds
    -0.14
    åij¼
    -0.14
    uced
    -0.14
    POSITIVE LOGITS
    bone
    0.20
    ingly
    0.18
    erals
    0.16
    μη
    0.15
    lett
    0.15
     Clarkson
    0.15
     Bones
    0.15
    Bone
    0.15
    apollo
    0.15
     bone
    0.15
    Act Density 0.029%

    No Known Activations