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

    Neuronpedia

    INDEX
    Explanations

    specific programming syntax and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    arrows indicating direction in technical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enthal
    -0.86
    edded
    -0.80
    mble
    -0.79
    ancies
    -0.76
    ened
    -0.75
    estern
    -0.73
    enance
    -0.72
    sson
    -0.71
    zzle
    -0.71
     Seym
    -0.69
    POSITIVE LOGITS
    flags
    0.74
     inherit
    0.69
    ²¾
    0.68
    OOL
    0.66
     Mongolia
    0.66
    =#
    0.64
     Route
    0.63
    Available
    0.63
    classes
    0.62
    ======
    0.62
    Act Density 0.006%

    No Known Activations