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

    Neuronpedia

    INDEX
    Explanations

    words related to speculation or likelihood

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    estern
    -0.94
    ilts
    -0.74
    ests
    -0.72
    atform
    -0.71
    restling
    -0.67
    ioch
    -0.66
    ainers
    -0.65
    leasing
    -0.63
    iership
    -0.62
    oning
    -0.61
    POSITIVE LOGITS
     innocuous
    0.93
     awfully
    0.92
     oddly
    0.92
     strangely
    0.88
     poised
    0.83
    rils
    0.81
     like
    0.81
     unstoppable
    0.80
     unlikely
    0.77
     suspicious
    0.76
    Act Density 0.052%

    No Known Activations