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

    Neuronpedia

    INDEX
    Explanations

    concepts related to reducing difficulty or promoting comfort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azzi
    -0.17
    ll
    -0.15
    unist
    -0.15
    lv
    -0.15
    opcion
    -0.14
    ipo
    -0.14
    ÑĻ
    -0.14
    ediator
    -0.14
    aries
    -0.14
    _PIXEL
    -0.14
    POSITIVE LOGITS
     dÃłng
    0.20
     burden
    0.19
     transitions
    0.17
     tensions
    0.16
     Restrictions
    0.16
     Bur
    0.16
     transition
    0.16
     tension
    0.16
     Transition
    0.15
    ucha
    0.15
    Act Density 0.021%

    No Known Activations