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

    Neuronpedia

    INDEX
    Explanations

    references to the absence or presence of specific individuals in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     الرياضيه
    -1.02
     незавершена
    -0.96
     pinulongan
    -0.94
    Portály
    -0.86
     الحره
    -0.83
    Portale
    -0.83
    -0.83
    Autoritní
    -0.82
    styleType
    -0.81
     ་་
    -0.80
    POSITIVE LOGITS
     same
    0.54
    he
    0.53
    pre
    0.51
     erroneously
    0.51
     mistakenly
    0.51
     Si
    0.49
    バンク
    0.48
     (
    0.48
    J
    0.48
    ja
    0.48
    Act Density 0.604%

    No Known Activations