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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ories
    -0.16
    ivol
    -0.15
    uml
    -0.14
    بÙĪد
    -0.14
    ughters
    -0.14
    vinc
    -0.14
    ä¼ģ
    -0.14
    boxes
    -0.13
    riz
    -0.13
     Principle
    -0.13
    POSITIVE LOGITS
    ÌĨ
    0.19
    INET
    0.17
    istes
    0.16
    Ì
    0.16
    æĤŁ
    0.15
    md
    0.15
    ght
    0.15
    unner
    0.14
    mdl
    0.14
    marshall
    0.14
    Act Density 0.279%

    No Known Activations