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 contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jadi
    -0.15
    iras
    -0.14
    _SKIP
    -0.14
    illos
    -0.14
    icket
    -0.14
    illus
    -0.13
    ashtra
    -0.13
    arris
    -0.13
    usan
    -0.13
    ividual
    -0.13
    POSITIVE LOGITS
     object
    0.19
     consider
    0.18
     releg
    0.17
     incap
    0.17
     objeto
    0.17
     catalog
    0.17
     laure
    0.16
    objects
    0.16
     objects
    0.15
     Consider
    0.15
    Act Density 0.021%

    No Known Activations