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

    Neuronpedia

    INDEX
    Explanations

    instances of structured text or mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical inequalities involving beta

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ddelweddau
    -0.58
     pleaſure
    -0.58
    -------------</
    -0.56
     nakalista
    -0.55
     &___
    -0.54
    zegor
    -0.54
     camiset
    -0.53
    rictions
    -0.52
    ectoria
    -0.52
    fören
    -0.52
    POSITIVE LOGITS
    <td>
    0.38
    ValueStyle
    0.37
    Normdaten
    0.34
    enumi
    0.34
    sort
    0.33
    sea
    0.33
     hängen
    0.33
    larg
    0.32
    ├──
    0.32
    生
    0.32
    Act Density 0.007%

    No Known Activations