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

    Neuronpedia

    INDEX
    Explanations

    words related to simplicity or lack of complication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izations
    -0.17
    ization
    -0.16
    æŦ
    -0.14
    .Ptr
    -0.14
    isation
    -0.14
    pointer
    -0.14
    ifications
    -0.14
    Sizer
    -0.14
    utions
    -0.14
    isations
    -0.14
    POSITIVE LOGITS
    oppable
    0.30
    rollable
    0.26
    /un
    0.24
    gable
    0.23
    ables
    0.23
    ifiable
    0.22
    achable
    0.21
    ventional
    0.21
    odox
    0.20
    okable
    0.20
    Act Density 0.034%

    No Known Activations