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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the pronoun "I" and phrases indicating personal experience or involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -resources
    -0.17
    igo
    -0.14
     Wich
    -0.14
    Ī¬
    -0.13
    ileged
    -0.13
     dừng
    -0.13
    .gstatic
    -0.13
    ioso
    -0.13
    imenti
    -0.13
     Gib
    -0.13
    POSITIVE LOGITS
     terr
    0.23
     dispatch
    0.23
     bankrupt
    0.21
     score
    0.20
     torch
    0.20
     van
    0.20
     bag
    0.19
     net
    0.19
    Dispatch
    0.19
     alien
    0.19
    Act Density 0.050%

    No Known Activations