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

    Neuronpedia

    INDEX
    Explanations

    references to project phases in a technical or development context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nga
    -0.20
    ness
    -0.19
    rest
    -0.18
    ente
    -0.17
    rec
    -0.17
    nn
    -0.17
    ner
    -0.17
    series
    -0.16
    ent
    -0.16
    hausen
    -0.15
    POSITIVE LOGITS
    hift
    0.23
    (phase
    0.18
    coach
    0.18
    ë³Ħ
    0.16
    /full
    0.15
    stery
    0.15
    outed
    0.15
    ONGL
    0.14
    -shift
    0.14
    Ùħا
    0.14
    Act Density 0.013%

    No Known Activations