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

    Neuronpedia

    INDEX
    Explanations

    numerical values and specific identifiers related to organizations or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xFB
    -0.13
    chn
    -0.13
    lass
    -0.13
    vinfos
    -0.13
    orda
    -0.13
     Eh
    -0.13
    ALTH
    -0.12
    IGHL
    -0.12
    bourg
    -0.12
    lic
    -0.12
    POSITIVE LOGITS
     PE
    0.45
    PE
    0.41
     VE
    0.40
     YE
    0.39
     CE
    0.39
    JE
    0.39
     JE
    0.38
     NE
    0.38
     SE
    0.38
     AE
    0.38
    Act Density 0.125%

    No Known Activations