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

    Neuronpedia

    INDEX
    Explanations

    words related to separation or disassociation

    oai_token-act-pair · gpt-3.5-turbo

    words associated with association, disassociation, and concepts of freedom or immunity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abyte
    -0.67
    odder
    -0.65
     odds
    -0.65
     WATCHED
    -0.61
     SEM
    -0.58
     table
    -0.56
     Byz
    -0.56
    numbered
    -0.55
     ob
    -0.54
     ::
    -0.54
    POSITIVE LOGITS
    owship
    0.94
     oneself
    0.90
     everybody
    0.81
     pupils
    0.78
     everyone
    0.78
    ment
    0.78
     addicts
    0.78
     subscribers
    0.74
    ament
    0.72
     wearer
    0.70
    Act Density 0.280%

    No Known Activations