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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "won" indicating victories or successes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eing
    -0.18
    že
    -0.17
    gone
    -0.15
    bones
    -0.15
    eval
    -0.15
    ev
    -0.15
    tin
    -0.15
    ÂĿ
    -0.15
    žil
    -0.14
    asl
    -0.14
    POSITIVE LOGITS
    't
    0.41
    ’t
    0.40
    kish
    0.22
    ;t
    0.20
    ´t
    0.19
     not
    0.19
    ky
    0.19
    ä¸įäºĨ
    0.19
    DER
    0.18
    'T
    0.18
    Act Density 0.010%

    No Known Activations