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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating movement or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entire
    -0.16
    ãģıãģł
    -0.15
    olini
    -0.15
    andes
    -0.14
    AYS
    -0.14
    ona
    -0.14
    onas
    -0.14
    ÙĪبة
    -0.13
     Harbour
    -0.13
    vÄĽdom
    -0.13
    POSITIVE LOGITS
    коз
    0.15
     another
    0.14
     detriment
    0.14
     ØŃÙĬØ«
    0.14
    noch
    0.14
    unch
    0.14
    ugg
    0.14
    uten
    0.14
    sis
    0.13
    vens
    0.13
    Act Density 0.127%

    No Known Activations