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

    Neuronpedia

    INDEX
    Explanations

    references to freedom and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antan
    -0.17
    ryan
    -0.16
    aul
    -0.15
    .sheet
    -0.14
    fu
    -0.14
    ored
    -0.14
    fn
    -0.14
    c
    -0.14
    sel
    -0.14
    ardi
    -0.14
    POSITIVE LOGITS
    quent
    0.26
    udent
    0.23
    ddie
    0.23
    estyle
    0.22
    inkel
    0.22
    QUENCY
    0.21
    edom
    0.20
    itas
    0.19
    unds
    0.19
     fre
    0.19
    Act Density 0.009%

    No Known Activations