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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Searching
    -0.18
    Searching
    -0.17
     yoktur
    -0.16
    еÑģÑĤÑĮ
    -0.16
    arma
    -0.15
    _blocking
    -0.15
     Supporting
    -0.15
    ÑĢеж
    -0.15
     suppress
    -0.14
    handling
    -0.14
    POSITIVE LOGITS
     being
    0.44
     becoming
    0.44
     getting
    0.34
    being
    0.33
     happening
    0.31
     coming
    0.31
     beginning
    0.29
     sendo
    0.27
     going
    0.26
     siendo
    0.26
    Act Density 0.503%

    No Known Activations