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

    Neuronpedia

    INDEX
    Explanations

    phrases related to executive roles and formal announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abus
    -0.15
    itos
    -0.15
    iona
    -0.14
    sdale
    -0.14
    aldo
    -0.13
    Coach
    -0.13
    alto
    -0.13
     hÆ°
    -0.13
    ewan
    -0.13
    iless
    -0.13
    POSITIVE LOGITS
     executives
    0.19
     Same
    0.19
     Sat
    0.19
     officials
    0.18
     outgoing
    0.18
     vice
    0.18
     exec
    0.17
    Same
    0.16
    Exec
    0.16
     Deep
    0.15
    Act Density 0.129%

    No Known Activations