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

    Neuronpedia

    INDEX
    Explanations

    phrases that express gratitude or highlight positive outcomes

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

    following "for *once*" or related adverbs

    np_acts-logits-general · gemini-2.0-flash

    rare/finally happening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sobie
    -0.35
     térmico
    -0.34
     térmica
    -0.32
     zvuky
    -0.32
     tarifa
    -0.31
    enterOuterAlt
    -0.31
     verder
    -0.31
    internalType
    -0.30
    providedIn
    -0.28
     fui
    -0.27
    POSITIVE LOGITS
    Autoritní
    0.62
     незавершена
    0.61
    罕
    0.58
     FINALLY
    0.55
    nodoc
    0.55
    dafx
    0.54
     Eſ
    0.54
    //
    0.54
    :✨
    0.54
    rare
    0.53
    Act Density 0.272%

    No Known Activations