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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating diverse origins or backgrounds of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilion
    -0.18
    _stdio
    -0.16
    loff
    -0.15
    atif
    -0.14
     anyone
    -0.14
    alendar
    -0.14
    heiro
    -0.14
    erli
    -0.14
    671
    -0.14
     anybody
    -0.14
    POSITIVE LOGITS
     around
    0.44
     across
    0.36
     throughout
    0.35
    around
    0.32
     backgrounds
    0.31
     Around
    0.30
     autour
    0.28
    Around
    0.27
     near
    0.23
     all
    0.22
    Act Density 0.057%

    No Known Activations