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

    Neuronpedia

    INDEX
    Explanations

    pronouns that indicate the reader's potential experiences or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oproject
    -0.15
     Mayer
    -0.15
    inspace
    -0.15
    erus
    -0.15
    umat
    -0.14
    imore
    -0.14
    Äĥm
    -0.14
    ÏĦικ
    -0.14
    toi
    -0.14
    ÙĨØ´
    -0.14
    POSITIVE LOGITS
     sure
    0.23
    _defs
    0.19
    'll
    0.19
     will
    0.18
    sure
    0.18
     guaranteed
    0.16
     Sure
    0.16
    ’ll
    0.16
     certainty
    0.16
     WILL
    0.15
    Act Density 0.059%

    No Known Activations