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

    Neuronpedia

    INDEX
    Explanations

    phrases related to "potential" or "potentially"

    oai_token-act-pair · gpt-3.5-turbo

    references to "pot" or "potential."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     silence
    -0.70
    IGH
    -0.63
     simultane
    -0.62
     obser
    -0.61
     rendition
    -0.58
     covenant
    -0.57
     trib
    -0.57
     Prosecut
    -0.57
     subord
    -0.56
     Thought
    -0.55
    POSITIVE LOGITS
    assium
    1.49
    atoes
    1.41
    tery
    1.41
    entially
    1.33
    luck
    1.29
    pour
    1.21
    ting
    1.13
    ential
    1.08
    ato
    1.01
    entials
    0.99
    Act Density 0.030%

    No Known Activations