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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility and necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.68
     Agre
    -0.65
     merec
    -0.65
     tibi
    -0.64
     humaine
    -0.63
     berätt
    -0.63
     scris
    -0.62
    ulemon
    -0.62
     ſche
    -0.62
     nucléaire
    -0.61
    POSITIVE LOGITS
     start
    0.74
     make
    0.74
     walk
    0.72
     be
    0.72
     go
    0.67
     take
    0.63
     get
    0.62
    reicht
    0.61
     ControllerBase
    0.61
     Schließlich
    0.60
    Act Density 0.316%

    No Known Activations