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

    Neuronpedia

    INDEX
    Explanations

    terms related to competition and performance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mana
    -0.16
    ega
    -0.16
     Tong
    -0.15
    icator
    -0.15
    .FontStyle
    -0.15
     hol
    -0.14
    ť
    -0.14
    ä¸ĸç´Ģ
    -0.14
    ãĥ¬ãĥĥãĥĪ
    -0.14
    еление
    -0.14
    POSITIVE LOGITS
     alone
    0.26
     Alone
    0.22
    alone
    0.21
     instead
    0.19
     rather
    0.18
    instead
    0.17
    ileo
    0.16
    ä»ĭ
    0.15
     Calder
    0.15
    entes
    0.14
    Act Density 0.246%

    No Known Activations