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

    Neuronpedia

    INDEX
    Explanations

    phrases related to programming and coding concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    brace
    -0.73
    livion
    -0.70
    plete
    -0.70
    jong
    -0.68
    ENCE
    -0.66
    UME
    -0.66
    etz
    -0.66
    uild
    -0.65
    MK
    -0.65
    berus
    -0.63
    POSITIVE LOGITS
     earliest
    1.21
     reasons
    1.17
     easiest
    1.13
     biggest
    1.12
     hardest
    1.12
     greatest
    1.10
     strang
    1.07
     coolest
    1.06
     simplest
    1.02
     brightest
    1.01
    Act Density 0.061%

    No Known Activations