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

    Neuronpedia

    INDEX
    Explanations

    the infinitive form of verbs, particularly the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portale
    -1.07
    Gambas
    -1.04
    extAlignment
    -0.98
     MainAxisSize
    -0.94
    Portail
    -0.92
    IntoConstraints
    -0.91
    RuleContext
    -0.87
    EndGlobalSection
    -0.86
     Савезне
    -0.83
    TintMode
    -0.82
    POSITIVE LOGITS
     can
    0.70
     who
    0.62
     
    0.55
    0.52
     must
    0.51
     make
    0.50
     should
    0.49
    で
    0.49
     has
    0.48
     で
    0.48
    Act Density 0.502%
    No Known Activations