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

    Neuronpedia

    INDEX
    Explanations

    document structure markers or placeholders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.07
    GeoNames
    -1.01
     Cæsar
    -0.99
    DeleteBehavior
    -0.98
    "]];
    -0.96
    ."));
    -0.95
     tartalomajánló
    -0.94
     iſt
    -0.93
     myſelf
    -0.92
     BRARY
    -0.92
    POSITIVE LOGITS
    .
    0.71
    ,
    0.71
     "
    0.62
     .
    0.61
    :
    0.60
    …
    0.59
     تانيه
    0.57
    ?
    0.57
    ...
    0.56
    !
    0.56
    Act Density 0.021%

    No Known Activations