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

    Neuronpedia

    INDEX
    Explanations

    numerical inquiries and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Whilst
    -0.65
     Amongst
    -0.65
     –
    -0.59
     optimise
    -0.54
    Whilst
    -0.54
     optimised
    -0.54
    …
    -0.52
     emperador
    -0.51
     realising
    -0.51
     realised
    -0.51
    POSITIVE LOGITS
    رشف
    0.80
    ")));
    0.80
     transfieras
    0.79
    DebuggerNonUser
    0.77
     beginnetje
    0.76
    OGND
    0.73
     ་་
    0.72
     ویکی‌پدی
    0.72
    NUMX
    0.71
     pinulongan
    0.69
    Act Density 0.054%

    No Known Activations