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

    Neuronpedia

    INDEX
    Explanations

    words related to future possibilities or potentials

    oai_token-act-pair · gpt-3.5-turbo

    references to potential or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orian
    -0.74
    winter
    -0.71
     Alone
    -0.69
    Newsletter
    -0.69
     ¶
    -0.68
     Digest
    -0.65
    erey
    -0.65
     ãĤµ
    -0.63
    orians
    -0.62
     Celebr
    -0.61
    POSITIVE LOGITS
     potential
    3.63
     Potential
    2.65
     possibilities
    2.00
     possible
    1.90
     prospective
    1.87
     potentially
    1.77
     possibility
    1.74
     prospects
    1.56
     opportunities
    1.30
     likelihood
    1.29
    Act Density 0.024%

    No Known Activations