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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĥ½å¤Ł
    -0.20
     being
    -0.18
     able
    -0.18
    ABLE
    -0.18
    èĥ½
    -0.18
    being
    -0.17
    -being
    -0.17
     ability
    -0.17
     Ability
    -0.15
    меÑĤÑĮ
    -0.15
    POSITIVE LOGITS
     easily
    0.31
     traced
    0.25
     Easily
    0.21
     liken
    0.20
    anything
    0.20
     anything
    0.20
     anywhere
    0.19
     readily
    0.19
    Anywhere
    0.19
     eas
    0.18
    Act Density 0.132%

    No Known Activations