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

    Neuronpedia

    INDEX
    Explanations

    phrases related to monetary rewards or penalties

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating potential limits or maximum values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    士
    -0.58
     Mistress
    -0.57
     Mate
    -0.57
     Abyss
    -0.57
     bitters
    -0.56
     Grimoire
    -0.55
     Narc
    -0.55
     Aliens
    -0.55
     Cele
    -0.54
     mistress
    -0.53
    POSITIVE LOGITS
    regulation
    1.12
    regulated
    1.05
    graded
    1.00
    grading
    1.00
    sized
    0.99
    grades
    0.99
    raised
    0.98
    votes
    0.96
    rights
    0.96
    dating
    0.94
    Act Density 0.039%

    No Known Activations