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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical symbols

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Coulter
    -0.69
    icz
    -0.68
    heimer
    -0.67
    Ey
    -0.66
    Bone
    -0.66
    gow
    -0.65
    hig
    -0.64
    isms
    -0.63
    æĢ
    -0.63
    anship
    -0.63
    POSITIVE LOGITS
     <!--
    0.82
     sudo
    0.76
     9
    0.74
     Next
    0.74
     5
    0.73
     namespace
    0.73
     cd
    0.71
    ĺħ
    0.71
     /**
    0.69
     //[
    0.69
    Act Density 0.031%

    No Known Activations