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

    Neuronpedia

    INDEX
    Explanations

    specific formatting or structural elements within the text, such as figures and section numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     мәкал
    -1.00
    IVEREF
    -1.00
    Geplaatst
    -0.95
     typelib
    -0.94
    __":
    -0.92
    Demografie
    -0.89
     دیکھیے
    -0.88
     <<<<<<<<<<<<<<
    -0.87
     rhestr
    -0.87
     nakalista
    -0.86
    POSITIVE LOGITS
     scales
    0.53
    Scale
    0.52
    ط
    0.50
    <sub>
    0.49
     scale
    0.47
    </td>
    0.46
     Scale
    0.45
     صف
    0.45
    springframework
    0.45
    scale
    0.44
    Act Density 0.492%

    No Known Activations