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

    Neuronpedia

    INDEX
    Explanations

    terms related to orientation and alignment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     x
    -0.55
     &
    -0.55
     A
    -0.52
     
    -0.51
    <eos>
    -0.49
     As
    -0.49
     +
    -0.49
    ↵↵
    -0.48
    printStackTrace
    -0.48
     i
    -0.47
    POSITIVE LOGITS
     Houſe
    0.91
     purpoſe
    0.87
     Inscrivez
    0.87
     Reſ
    0.87
     Theſe
    0.87
     credentials
    0.86
     Anſ
    0.85
    ÍTULO
    0.84
     ་་
    0.84
     متعلقه
    0.83
    Act Density 0.120%

    No Known Activations