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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and coordinating phrases that indicate relationships and connections between ideas

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

    and verbs or to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Houſe
    -0.59
    carbonyl
    -0.53
     Majefty
    -0.52
     itemName
    -0.49
    borderSide
    -0.48
    featureID
    -0.48
     imageName
    -0.48
    casio
    -0.47
    rawDesc
    -0.47
     sessionId
    -0.46
    POSITIVE LOGITS
    hygiène
    0.60
    üyada
    0.59
     to
    0.51
    enfance
    0.50
    interprétation
    0.50
    esercito
    0.50
    obiettivo
    0.48
    humanité
    0.47
    amitié
    0.45
     Mullins
    0.45
    Act Density 0.417%

    No Known Activations