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

    Neuronpedia

    INDEX
    Explanations

    instances of conjunctions and transitional phrases

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

    following conjunctions

    np_acts-logits-general · gemini-2.0-flash

    trust and believe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onItemClick
    -0.62
    fromnode
    -0.61
     vidare
    -0.58
    ::~
    -0.57
    maro
    -0.54
    basicConfig
    -0.54
    ::_('
    -0.54
    మూ
    -0.53
    Viitteet
    -0.53
    setLayoutParams
    -0.52
    POSITIVE LOGITS
     trust
    2.06
    trust
    1.79
     Trust
    1.78
    Trust
    1.76
    Believe
    1.65
     Believe
    1.64
     believe
    1.62
     TRUST
    1.58
    believe
    1.53
    TRUST
    1.42
    Act Density 0.285%

    No Known Activations