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

    Neuronpedia

    INDEX
    Explanations

    the pronoun "who" and its references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.34
     Efq
    -1.26
     Jefus
    -1.16
    ^(@)
    -1.13
     Anſ
    -1.11
     theſe
    -1.10
     doubtnut
    -1.09
     ་་
    -1.09
     Majefty
    -1.08
    ConstraintMaker
    -1.07
    POSITIVE LOGITS
    <eos>
    0.82
     to
    0.82
     who
    0.81
     
    0.74
     if
    0.72
     in
    0.72
     the
    0.71
     or
    0.70
     for
    0.68
     I
    0.68
    Act Density 0.115%

    No Known Activations