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

    Neuronpedia

    INDEX
    Explanations

    actionable phrases that relate to guidance or instruction in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -1.49
    expandindo
    -1.29
    extAlignment
    -1.18
    +#+#
    -1.18
     дописавши
    -1.16
    ########.
    -1.13
    Vidite
    -1.11
     tartalomajánló
    -1.07
     estekak
    -1.07
    GEBURTSDATUM
    -1.06
    POSITIVE LOGITS
     
    0.81
    ,
    0.64
    .
    0.59
     (
    0.58
     “
    0.58
    2
    0.57
    ↵↵
    0.55
     $
    0.55
    :
    0.55
    -
    0.54
    Act Density 4.619%

    No Known Activations