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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to mathematical processes and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kara
    -0.15
    cient
    -0.14
    _DEV
    -0.14
    ssql
    -0.13
    ifo
    -0.13
    oce
    -0.13
     centerX
    -0.13
     keyst
    -0.13
    awe
    -0.13
    ureka
    -0.13
    POSITIVE LOGITS
     space
    0.30
    space
    0.27
    ospace
    0.26
     spaces
    0.26
    .space
    0.24
     underlying
    0.24
    _space
    0.23
     пÑĢоÑģÑĤÑĢан
    0.22
     Space
    0.22
    -space
    0.21
    Act Density 0.121%

    No Known Activations