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

    Neuronpedia

    INDEX
    Explanations

    the word 'collective' or related variations

    oai_token-act-pair · gpt-3.5-turbo

    references to collective concepts or collective actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.77
    ocrates
    -0.75
    lyn
    -0.73
    geon
    -0.73
    cale
    -0.70
    ĺħ
    -0.68
    tenance
    -0.68
    geons
    -0.68
    ĪĴ
    -0.67
     Racer
    -0.67
    POSITIVE LOGITS
     bargaining
    1.18
     collective
    0.84
    think
    0.79
     effort
    0.77
     membership
    0.76
     endeavour
    0.76
    ivities
    0.74
     ACTIONS
    0.73
     conscience
    0.70
    iser
    0.70
    Act Density 0.022%

    No Known Activations