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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "when" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isu
    -0.19
    halb
    -0.17
    HEMA
    -0.17
    -UA
    -0.15
    agini
    -0.15
     sublic
    -0.14
    bourg
    -0.14
    avou
    -0.14
    offs
    -0.14
    sense
    -0.14
    POSITIVE LOGITS
    soever
    0.17
    stered
    0.16
    -нибÑĥдÑĮ
    0.15
    abouts
    0.15
    arrow
    0.14
    anco
    0.14
    ç
    0.14
    æ°ı
    0.14
    oria
    0.13
    iras
    0.13
    Act Density 0.113%

    No Known Activations