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

    Neuronpedia

    INDEX
    Explanations

    terms related to guarantees and assurances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    luk
    -0.16
    FormsModule
    -0.15
    à¤ł
    -0.14
    arc
    -0.14
    lak
    -0.14
    stra
    -0.14
    croft
    -0.13
    ardi
    -0.13
     Meredith
    -0.13
    CREMENT
    -0.13
    POSITIVE LOGITS
     Journey
    0.17
    ourney
    0.15
    ifu
    0.15
    quo
    0.14
     Bott
    0.14
    otton
    0.14
    lich
    0.14
    ribly
    0.13
    IGO
    0.13
    -purpose
    0.13
    Act Density 0.015%

    No Known Activations