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

    Neuronpedia

    INDEX
    Explanations

    the pronoun "you" and variations thereof in different contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ſche
    -1.36
     pleaſure
    -1.35
     purpoſe
    -1.30
     itſelf
    -1.28
     Anſ
    -1.26
     Reſ
    -1.26
     houſe
    -1.24
     iſt
    -1.22
     Houſe
    -1.22
    ſelf
    -1.21
    POSITIVE LOGITS
    ty
    0.62
    ocyte
    0.62
    ocytes
    0.62
    ண்டும்
    0.62
     in
    0.58
     fee
    0.58
     I
    0.57
    pflicht
    0.56
    مانية
    0.56
    ículo
    0.55
    Act Density 0.004%

    No Known Activations