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

    Neuronpedia

    INDEX
    Explanations

    connections related to community building and collaborative systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umd
    -0.15
    adla
    -0.14
    threshold
    -0.14
    wert
    -0.14
    hor
    -0.14
    ç¯
    -0.14
    framework
    -0.13
     tack
    -0.13
     dich
    -0.13
    ikel
    -0.13
    POSITIVE LOGITS
     Mah
    0.21
     sal
    0.20
     discrimin
    0.18
    Mah
    0.18
     patterns
    0.17
     Patterns
    0.16
     structural
    0.16
    sal
    0.16
     pri
    0.16
     semantics
    0.16
    Act Density 0.062%

    No Known Activations