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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" and their various forms in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    instances of the verb "was" in past tense passive constructions describing actions or states.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     involved
    -0.47
     INVOLVED
    -0.39
    目に
    -0.36
     Involved
    -0.35
    involved
    -0.35
    Où
    -0.34
     reason
    -0.33
     reafon
    -0.32
     relevant
    -0.32
    yl
    -0.31
    POSITIVE LOGITS
     wearing
    0.83
    wearing
    0.73
    Wearing
    0.66
     Wearing
    0.65
     dressed
    0.60
    FunctionFlags
    0.59
     bukan
    0.57
    '])){
    0.56
     married
    0.55
    elry
    0.54
    Act Density 0.388%

    No Known Activations