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

    Neuronpedia

    INDEX
    Explanations

    phrases related to typical or common situations or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    descriptive terms related to classic and familiar situations or stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acers
    -0.83
    leased
    -0.80
    ufact
    -0.77
    ouses
    -0.75
    friends
    -0.74
    ributes
    -0.73
    omever
    -0.72
    orthy
    -0.72
    ifles
    -0.72
    ateurs
    -0.72
    POSITIVE LOGITS
     fallacy
    1.55
     dilemma
    1.38
     paradox
    1.36
     trope
    1.33
     phenomenon
    1.24
     irony
    1.13
     predicament
    1.12
     tendency
    1.12
     Catch
    1.11
     tactic
    1.10
    Act Density 0.462%

    No Known Activations