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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate inclusivity or variations within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odka
    -0.15
    .desktop
    -0.14
    ecer
    -0.14
    nici
    -0.14
    IBUTES
    -0.14
    isko
    -0.13
    esen
    -0.13
    icit
    -0.13
    uli
    -0.13
    assa
    -0.13
    POSITIVE LOGITS
    ziel
    0.15
    cco
    0.15
    SEX
    0.14
    Ability
    0.13
     Ability
    0.13
    uropean
    0.13
    tons
    0.13
     bil
    0.13
    herent
    0.13
    dux
    0.13
    Act Density 0.096%

    No Known Activations