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

    Neuronpedia

    INDEX
    Explanations

    phrases with the word "might."

    oai_token-act-pair · gpt-3.5-turbo

    speculative language regarding potential outcomes or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oric
    -0.90
    scar
    -0.69
    seller
    -0.68
    cake
    -0.67
    carbon
    -0.67
    vo
    -0.65
    chen
    -0.65
     Purpose
    -0.63
    zen
    -0.62
    ross
    -0.61
    POSITIVE LOGITS
     tremend
    0.99
     sugg
    0.94
     feas
    0.92
     plaus
    0.90
     conce
    0.88
    haps
    0.87
     mistakenly
    0.82
     confir
    0.78
    berra
    0.77
     ende
    0.77
    Act Density 0.029%

    No Known Activations