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

    Neuronpedia

    INDEX
    Explanations

    coordinating conjunctions and adjectives in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wiktionnaire
    -0.59
     fossero
    -0.53
    曖昧さ回避
    -0.51
     estekak
    -0.51
    rinfo
    -0.50
     newOwner
    -0.49
    homonymie
    -0.49
    herself
    -0.49
    TagMode
    -0.48
    erialized
    -0.46
    POSITIVE LOGITS
     profitable
    0.86
     dangerous
    0.85
     informative
    0.81
     impactful
    0.78
     extremely
    0.76
     instructive
    0.76
     deadly
    0.74
    profitable
    0.74
     scary
    0.72
     unpredictable
    0.72
    Act Density 0.340%

    No Known Activations