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

    Neuronpedia

    INDEX
    Explanations

    references to security and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    serter
    -0.16
    aster
    -0.15
    .yy
    -0.15
    .infinity
    -0.14
    eks
    -0.14
    ews
    -0.14
    оÑĪ
    -0.14
    sgi
    -0.14
    ouch
    -0.13
     Anast
    -0.13
    POSITIVE LOGITS
    tainment
    0.18
    thane
    0.17
    eper
    0.15
    ffen
    0.15
    ôte
    0.15
     plain
    0.15
    ipe
    0.14
    roma
    0.14
    pte
    0.14
    EH
    0.14
    Act Density 0.021%

    No Known Activations