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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sense of freshness or novelty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ist
    -0.16
    owns
    -0.14
    uce
    -0.14
    awan
    -0.13
    acak
    -0.13
     parts
    -0.13
    _procs
    -0.13
    fo
    -0.13
     McInt
    -0.13
    ord
    -0.12
    POSITIVE LOGITS
    hle
    0.17
    elden
    0.15
    ikat
    0.14
    latex
    0.14
    .trailing
    0.14
    reib
    0.14
    uhn
    0.14
    ifu
    0.14
    dept
    0.13
    ahren
    0.13
    Act Density 0.087%

    No Known Activations