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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing exclusivity or rarity of conditions, actions, or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \{\\
    -0.64
    }{*}{
    -0.56
    /*
    -0.56
    .*")]
    -0.55
     écoulé
    -0.52
    WEBPACK
    -0.51
    nieren
    -0.49
     发表于
    -0.48
     cjs
    -0.48
    LEAF
    -0.47
    POSITIVE LOGITS
    GEBURTSDATUM
    0.98
    only
    0.79
    Only
    0.75
    ONLY
    0.75
     wyłącznie
    0.74
    Только
    0.74
     only
    0.72
     Only
    0.72
    ่านั้น
    0.70
    только
    0.70
    Act Density 0.318%

    No Known Activations