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

    Neuronpedia

    INDEX
    Explanations

    expressions related to measurement and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enso
    -0.16
    acket
    -0.15
    orate
    -0.14
    ë²Į
    -0.14
    inia
    -0.14
    ãĤĩãģĨ
    -0.14
    apons
    -0.14
    outine
    -0.14
    motion
    -0.13
    limited
    -0.13
    POSITIVE LOGITS
    anas
    0.17
    croft
    0.17
     levels
    0.16
    arl
    0.16
     assort
    0.16
    XHR
    0.16
     level
    0.15
    _TB
    0.15
     lvl
    0.15
    levels
    0.15
    Act Density 0.228%

    No Known Activations