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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing strong beliefs or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong belief or endorsement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Settlement
    -0.74
    eon
    -0.74
    OTOS
    -0.72
    raltar
    -0.72
     Chaser
    -0.72
    oleon
    -0.72
     Procedure
    -0.72
     Tycoon
    -0.71
     Journals
    -0.71
     Corpse
    -0.71
    POSITIVE LOGITS
     enough
    0.92
     disagree
    0.78
     differentiated
    0.76
     correlated
    0.76
    ener
    0.75
     encouraged
    0.75
     incentiv
    0.75
     advise
    0.75
     discouraged
    0.74
    charged
    0.74
    Act Density 0.011%

    No Known Activations