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

    Neuronpedia

    INDEX
    Explanations

    mathematical terms and expressions related to probability and conditions within equations and proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vro
    -0.15
    StartPosition
    -0.15
    owa
    -0.15
    ibia
    -0.14
     جاÙħ
    -0.14
    _UNS
    -0.14
    chap
    -0.13
    orida
    -0.13
    วà¸ĩ
    -0.13
    ibr
    -0.13
    POSITIVE LOGITS
     Goldberg
    0.18
    erset
    0.17
    ystal
    0.14
    idel
    0.14
    ajs
    0.13
    ission
    0.13
     Bold
    0.13
     Neo
    0.13
    ervation
    0.13
    redient
    0.13
    Act Density 0.467%

    No Known Activations