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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or lack of knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¸Ńà¸Ķ
    -0.17
    bourg
    -0.15
    brew
    -0.14
    asad
    -0.13
    .eulerAngles
    -0.13
    Nonce
    -0.13
    hell
    -0.13
    олоÑģ
    -0.13
    ennen
    -0.13
    ety
    -0.13
    POSITIVE LOGITS
     else
    0.23
     except
    0.19
    except
    0.19
    _except
    0.16
     Nobody
    0.15
     Except
    0.14
    Except
    0.14
    avit
    0.14
     Else
    0.14
     board
    0.14
    Act Density 0.039%

    No Known Activations