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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" and its various forms in relation to professions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izon
    -0.15
    ens
    -0.15
    ajar
    -0.15
    anders
    -0.14
    NameValuePair
    -0.14
    ø
    -0.14
    enders
    -0.14
    ogram
    -0.13
    -CS
    -0.13
    achi
    -0.13
    POSITIVE LOGITS
    utschen
    0.15
    ï¸
    0.15
    phalt
    0.15
    ÏĦÏĥ
    0.15
    IRCLE
    0.14
     kne
    0.14
    vents
    0.13
     âĺĨ
    0.13
     طبÙĬ
    0.13
    ÑĨо
    0.13
    Act Density 0.044%

    No Known Activations