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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing strong opinions or evaluations on a topic

    oai_token-act-pair · gpt-3.5-turbo

    phrases that use "arguably" to present opinions or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nen
    -0.76
    ysis
    -0.68
    eries
    -0.68
    letter
    -0.68
    ters
    -0.66
     Simulator
    -0.66
     Purchase
    -0.66
    aeus
    -0.66
    spr
    -0.65
    iry
    -0.64
    POSITIVE LOGITS
     metic
    0.89
     deserved
    0.80
     underrated
    0.77
     unemploy
    0.76
     minded
    0.74
     disadvant
    0.70
     irreversible
    0.69
     conduc
    0.69
     incapable
    0.66
    ©¶æ¥µ
    0.66
    Act Density 0.016%

    No Known Activations