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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating pauses or connections in written text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    цездатний
    -0.80
     Efq
    -0.77
    ={`
    -0.73
    $.}
    -0.73
    IContainer
    -0.71
    Diweddarwch
    -0.70
     Penna
    -0.70
    ,//
    -0.69
    listdir
    -0.69
     stb
    -0.68
    POSITIVE LOGITS
     but
    0.84
     although
    0.84
     which
    0.81
     потому
    0.72
     hence
    0.69
     thus
    0.65
     though
    0.64
     particularly
    0.63
     including
    0.62
     because
    0.61
    Act Density 0.792%

    No Known Activations