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

    Neuronpedia

    INDEX
    Explanations

    words related to laws, legal issues, and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ob"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivities
    -0.78
    UAL
    -0.78
     waters
    -0.72
     Quan
    -0.68
     Insp
    -0.68
     Flan
    -0.68
    EngineDebug
    -0.67
     Falk
    -0.67
    HAHA
    -0.66
     ORIG
    -0.66
    POSITIVE LOGITS
    lique
    1.34
    ob
    1.23
    ilib
    1.23
    rien
    1.17
    edience
    1.17
    acter
    1.14
    esity
    1.13
    fusc
    1.01
    ols
    1.00
    edient
    1.00
    Act Density 0.007%

    No Known Activations