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

    Neuronpedia

    INDEX
    Explanations

    the presence of forms of the verb "to be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oyer
    -0.20
    ä¾
    -0.14
    ovice
    -0.14
    Unnamed
    -0.14
    zens
    -0.13
    armor
    -0.13
    Animating
    -0.13
    apter
    -0.13
    istine
    -0.13
    vore
    -0.13
    POSITIVE LOGITS
     among
    0.18
     professor
    0.16
     native
    0.16
     nothing
    0.15
     een
    0.15
     our
    0.15
     natives
    0.15
     from
    0.15
     originally
    0.15
    atz
    0.15
    Act Density 0.063%

    No Known Activations