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

    Neuronpedia

    INDEX
    Explanations

    instances of line breaks or separators in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mess
    -0.16
    assin
    -0.16
    icho
    -0.15
     Mess
    -0.15
    ubs
    -0.15
    Mess
    -0.15
    zel
    -0.15
    _CBC
    -0.15
    stk
    -0.15
    yu
    -0.15
    POSITIVE LOGITS
    ectomy
    0.15
     clue
    0.14
    Ùĩ
    0.14
     metros
    0.14
    شة
    0.13
    ortic
    0.13
     cle
    0.13
    enties
    0.13
    بÙĪر
    0.13
     Disposable
    0.13
    Act Density 0.001%

    No Known Activations