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

    Neuronpedia

    INDEX
    Explanations

    various forms of the verb "to be" and its related constructions indicating existence or states

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

    associated with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avoient
    -0.43
     auroit
    -0.40
     étoit
    -0.38
     spéciaux
    -0.38
     vectorielles
    -0.37
     käyt
    -0.36
     something
    -0.35
     nonUne
    -0.35
     چیزی
    -0.35
     mitään
    -0.35
    POSITIVE LOGITS
     involved
    0.70
     capable
    0.69
     weakly
    0.66
     strongly
    0.63
     able
    0.63
     quantitatively
    0.59
     found
    0.57
     mergeFrom
    0.56
    involved
    0.56
    AutoModerator
    0.56
    Act Density 0.478%

    No Known Activations