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

    Neuronpedia

    INDEX
    Explanations

    lines of code or code-related syntax

    oai_token-act-pair · gpt-3.5-turbo

    arrow or pointer symbols typically used in programming or navigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enthal
    -0.91
    mble
    -0.84
    estern
    -0.77
     Seym
    -0.77
    ament
    -0.76
    edded
    -0.75
    zzle
    -0.72
    amental
    -0.71
    ancies
    -0.71
    blers
    -0.69
    POSITIVE LOGITS
     inherit
    0.71
     Mongolia
    0.71
     Route
    0.69
    flags
    0.68
    ²¾
    0.67
     Result
    0.66
     IO
    0.65
     Pass
    0.64
    ======
    0.63
     cancel
    0.62
    Act Density 0.009%

    No Known Activations