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

    Neuronpedia

    INDEX
    Explanations

    references to comfort, completion, and assistance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ajas
    -0.19
    asu
    -0.16
    ĻĤ
    -0.15
    vero
    -0.15
    rada
    -0.15
    achs
    -0.15
    ÑĨин
    -0.15
    ourd
    -0.14
    ought
    -0.14
    Æ¡
    -0.14
    POSITIVE LOGITS
     Nunes
    0.15
     â
    0.14
    inha
    0.14
    lien
    0.13
    inh
    0.13
     gener
    0.13
     sole
    0.13
    ÙĨ
    0.12
     menn
    0.12
    _attachments
    0.12
    Act Density 0.681%

    No Known Activations