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

    Neuronpedia

    INDEX
    Explanations

    terms related to space-saving designs and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rych
    -0.15
    ntag
    -0.15
    hart
    -0.14
    plx
    -0.14
    ehr
    -0.14
    strup
    -0.14
     lon
    -0.14
    rzy
    -0.13
    797
    -0.13
    znik
    -0.13
    POSITIVE LOGITS
     space
    0.97
    space
    0.81
     Space
    0.78
    -space
    0.76
    空éĹ´
    0.74
    Space
    0.71
    _space
    0.70
     espacio
    0.66
     SPACE
    0.66
    .space
    0.63
    Act Density 0.196%

    No Known Activations