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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating timing or sequencing of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    first time, first goal, first hit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteAttribute
    -0.38
     bygg
    -0.34
    igshid
    -0.32
    PostBack
    -0.31
     réun
    -0.31
     privées
    -0.30
    çoivent
    -0.30
    誘
    -0.30
     économiques
    -0.30
    semver
    -0.29
    POSITIVE LOGITS
     throughout
    0.67
    throughout
    0.63
    Throughout
    0.60
     Throughout
    0.58
    AtEndOf
    0.57
     transfieras
    0.56
     للمعارف
    0.56
     disambiguazione
    0.52
    MemoryWarning
    0.52
    ficulties
    0.49
    Act Density 0.173%

    No Known Activations