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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and syntactic elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hea
    -0.17
     trib
    -0.16
    verage
    -0.15
    enza
    -0.15
    attering
    -0.14
    ayan
    -0.14
    HE
    -0.14
    mons
    -0.14
    attern
    -0.14
    ypad
    -0.13
    POSITIVE LOGITS
    лаÑĪ
    0.15
    ulton
    0.15
    fi
    0.14
    ford
    0.14
     Coalition
    0.14
    alaxy
    0.14
    eful
    0.14
    rozen
    0.14
    ocker
    0.14
    дам
    0.14
    Act Density 0.331%

    No Known Activations