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

    Neuronpedia

    INDEX
    Explanations

    statements concerning the concept of claiming or discussing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wer
    -0.49
    </table>
    -0.48
     somit
    -0.48
     G
    -0.46
     bau
    -0.45
    gab
    -0.45
     uno
    -0.45
    RAFT
    -0.44
    Wer
    -0.43
     g
    -0.43
    POSITIVE LOGITS
    saying
    1.03
    Saying
    1.02
     Saying
    0.99
     saying
    0.99
     ProtoMessage
    0.96
    say
    0.94
     say
    0.93
    SAY
    0.92
    Says
    0.91
     sagt
    0.91
    Act Density 0.160%

    No Known Activations