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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to privacy policies and user agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ering
    -0.16
    meld
    -0.16
     mult
    -0.15
     Hij
    -0.15
    erable
    -0.15
    emes
    -0.14
    ILT
    -0.14
    lement
    -0.14
    ÅĻÃŃ
    -0.14
    caster
    -0.14
    POSITIVE LOGITS
    /ag
    0.15
    åIJĮæĦı
    0.15
    é¼
    0.15
    aren
    0.15
     bitmask
    0.15
    ALSE
    0.14
     participation
    0.14
     tac
    0.14
     Michaels
    0.14
     Builders
    0.14
    Act Density 0.063%

    No Known Activations