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

    Neuronpedia

    INDEX
    Explanations

    instances of the pronoun "we" and associated verbs indicating involvement or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.22
    ſelf
    -1.14
     Jefus
    -1.13
    IVEREF
    -1.06
     itſelf
    -1.05
     Shakspeare
    -1.04
    GEBURTSDATUM
    -1.04
     pleaſure
    -1.01
     Majefty
    -1.01
     ProtoMessage
    -1.01
    POSITIVE LOGITS
     a
    0.68
     also
    0.63
     
    0.60
     specifically
    0.59
     bort
    0.56
     use
    0.56
     deal
    0.54
     pre
    0.53
     need
    0.52
     consider
    0.52
    Act Density 0.648%

    No Known Activations