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

    Neuronpedia

    INDEX
    Explanations

    complex philosophical concepts and discussions about the mind and perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancel
    -0.16
    Ŀi
    -0.15
     Barcl
    -0.15
    imli
    -0.14
    ôm
    -0.14
     तम
    -0.14
     Salisbury
    -0.14
     ì²
    -0.13
    ctl
    -0.13
     literature
    -0.13
    POSITIVE LOGITS
     Logical
    0.22
     Desc
    0.22
     Hus
    0.21
     Emp
    0.21
    Desc
    0.21
     Berkeley
    0.20
     Russell
    0.20
     Hemp
    0.19
     logical
    0.19
     Carn
    0.19
    Act Density 0.040%

    No Known Activations