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

    Neuronpedia

    INDEX
    Explanations

    phrases typically associated with knowledge sharing or educational content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fabrics
    -0.15
    aven
    -0.15
    onden
    -0.15
    üp
    -0.14
    paque
    -0.14
     compact
    -0.13
    оÑģÑĮ
    -0.13
    -eye
    -0.13
    otate
    -0.13
     ther
    -0.13
    POSITIVE LOGITS
    irsch
    0.17
    HLT
    0.15
    pNet
    0.15
    addtogroup
    0.14
    inded
    0.14
     Twist
    0.14
    etta
    0.14
    iram
    0.14
    -eslint
    0.14
    iser
    0.13
    Act Density 0.045%

    No Known Activations