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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of association

    oai_token-act-pair · gpt-3.5-turbo

    mention of "association" or related terms signifying connections or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gm
    -0.70
    =-=-=-=-=-=-=-=-
    -0.69
    cale
    -0.68
    fare
    -0.68
    stall
    -0.65
    sets
    -0.64
    stals
    -0.63
    iak
    -0.61
    ardless
    -0.61
    onds
    -0.61
    POSITIVE LOGITS
     associations
    1.02
     association
    0.90
     affili
    0.90
    eer
    0.89
    eering
    0.86
    ality
    0.85
    esthesia
    0.79
    ually
    0.78
    ociation
    0.74
    SHIP
    0.73
    Act Density 0.016%

    No Known Activations