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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various forms and tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    моÑĢ
    -0.15
     Dispatch
    -0.15
    .nodeType
    -0.15
    oplast
    -0.15
    hardt
    -0.14
    ienes
    -0.14
    owe
    -0.13
     handful
    -0.13
    LR
    -0.13
    ove
    -0.13
    POSITIVE LOGITS
    ÑģÑĤÑĮ
    0.15
    ERSHEY
    0.15
     ведÑĮ
    0.15
    eza
    0.14
    tty
    0.14
    ÑģÑĮ
    0.14
    ži
    0.14
    ppers
    0.14
    -ignore
    0.14
    ESC
    0.13
    Act Density 0.154%

    No Known Activations