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

    Neuronpedia

    INDEX
    Explanations

    code snippets and programming-related structures

    oai_token-act-pair · gpt-3.5-turbo

    arrows indicating flow or direction in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anmar
    -0.86
    enthal
    -0.84
    ancies
    -0.82
    icult
    -0.78
    jri
    -0.77
    ventus
    -0.75
    isf
    -0.75
    iage
    -0.75
    unci
    -0.74
    iren
    -0.74
    POSITIVE LOGITS
     IO
    0.96
     ({
    0.77
     [];
    0.75
     Result
    0.75
     *)
    0.72
     {:
    0.71
     {
    0.71
     [(
    0.69
     Relations
    0.68
     ()
    0.67
    Act Density 0.029%

    No Known Activations