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

    Neuronpedia

    INDEX
    Explanations

    references to specific ideas or items in a discussion

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -1.09
    
    -1.07
    extAlignment
    -1.05
     TextAlign
    -0.98
     MainAxisSize
    -0.98
    BufferException
    -0.98
    脚注の使い方
    -0.98
     للمعارف
    -0.97
    ientôt
    -0.93
     estekak
    -0.91
    POSITIVE LOGITS
    .
    0.63
     later
    0.62
    ;
    0.55
    !
    0.54
     as
    0.53
    later
    0.51
     in
    0.50
    Later
    0.50
    ?
    0.50
    :
    0.49
    Act Density 0.059%

    No Known Activations