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

    Neuronpedia

    INDEX
    Explanations

    special characters or symbols commonly used in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elts
    -0.08
    ÑĥÑģÑĤа
    -0.08
     Artifact
    -0.07
    ewan
    -0.07
     Arte
    -0.07
    _nf
    -0.07
    bih
    -0.07
    uner
    -0.07
    shaw
    -0.06
    ĥĿ
    -0.06
    POSITIVE LOGITS
    IRST
    0.06
    096
    0.06
     Maher
    0.06
    约
    0.06
     mon
    0.06
    ï¸
    0.06
    487
    0.05
    grounds
    0.05
    غÙĨ
    0.05
    swer
    0.05
    Act Density 0.001%

    No Known Activations