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

    Neuronpedia

    INDEX
    Explanations

    terms related to data collection and information processing

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

    Followed by the word "is"

    np_acts-logits-general · gemini-2.0-flash

    describing technical entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     this
    -0.79
    oredCriteria
    -0.74
     ModelExpression
    -0.64
     betweenstory
    -0.63
    ✭
    -0.61
     thereon
    -0.61
     such
    -0.60
    this
    -0.60
     propOrder
    -0.60
    such
    -0.60
    POSITIVE LOGITS
     /^\
    0.60
     alone
    0.59
     particular
    0.57
    แห
    0.56
     maravilh
    0.56
     👆
    0.54
     particulière
    0.54
     específico
    0.53
    particular
    0.52
     ALONE
    0.51
    Act Density 0.535%

    No Known Activations