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

    Neuronpedia

    INDEX
    Explanations

    semicolon characters that typically indicate the end of statements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused17>
    -1.10
    <unused74>
    -1.10
    <unused41>
    -1.10
    <unused68>
    -1.10
    <unused23>
    -1.10
    <unused3>
    -1.10
    <unused28>
    -1.10
    <unused8>
    -1.09
    [@BOS@]
    -1.09
    <pad>
    -1.09
    POSITIVE LOGITS
    ;
    0.45
     ;
    0.35
     húmedo
    0.33
     Jerusalén
    0.31
    ';
    0.31
    );
    0.29
     amarillas
    0.29
    ?
    0.29
     læng
    0.28
     său
    0.28
    Act Density 0.001%

    No Known Activations