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

    Neuronpedia

    INDEX
    Explanations

    coded structures and data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sel
    -0.53
     Ch
    -0.50
     sign
    -0.49
     Pin
    -0.48
     البي
    -0.47
     various
    -0.47
     Sign
    -0.46
     
    -0.46
    BIND
    -0.46
     g
    -0.46
    POSITIVE LOGITS
     Monfieur
    0.92
     Majefty
    0.87
     Efq
    0.85
     houſe
    0.84
     purpoſe
    0.83
     pleaſure
    0.83
     ſtate
    0.83
     myſelf
    0.80
    FormTagHelper
    0.78
     ſever
    0.77
    Act Density 0.578%

    No Known Activations