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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions related to decision-making and personal agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arkin
    -0.15
    Ì
    -0.15
    ģm
    -0.14
    adol
    -0.14
    ople
    -0.14
    shint
    -0.14
    agt
    -0.14
    ching
    -0.13
    UCT
    -0.13
    hed
    -0.13
    POSITIVE LOGITS
    _MARKER
    0.16
    -scrollbar
    0.15
    åį
    0.15
     TableRow
    0.15
    jal
    0.15
    INLINE
    0.15
    elpers
    0.14
    isin
    0.14
    ربÛĮ
    0.14
     OTHERWISE
    0.14
    Act Density 0.571%

    No Known Activations