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

    Neuronpedia

    INDEX
    Explanations

    the presence of qualifiers and descriptors that suggest a typical or expected state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coni
    -0.15
    DEX
    -0.15
    tein
    -0.15
    bsd
    -0.15
    Wunused
    -0.15
    aniem
    -0.15
    èĻij
    -0.15
    presso
    -0.14
    é¡
    -0.14
    clist
    -0.14
    POSITIVE LOGITS
     finally
    0.16
    ure
    0.15
     Simmons
    0.15
     normally
    0.15
     Bilg
    0.14
    790
    0.14
    æľ«
    0.14
    silent
    0.14
    ra
    0.14
    ures
    0.14
    Act Density 0.212%

    No Known Activations