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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a change in situation or unexpected outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idan
    -0.19
    ime
    -0.17
    cki
    -0.15
     èij
    -0.15
    agem
    -0.15
     unprotected
    -0.15
    imes
    -0.15
    ist
    -0.14
     çĿ
    -0.14
    uset
    -0.14
    POSITIVE LOGITS
     into
    0.17
    caff
    0.16
     onCancelled
    0.15
    nout
    0.15
     out
    0.15
    شتر
    0.15
    LayoutPanel
    0.14
    owie
    0.14
    tail
    0.14
    ůst
    0.14
    Act Density 0.015%

    No Known Activations