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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with manipulation and behavioral influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VENTORY
    -0.15
    kyt
    -0.15
    -flex
    -0.14
     Buk
    -0.13
     sav
    -0.13
    Selective
    -0.13
     selectively
    -0.13
    alfa
    -0.13
    utton
    -0.13
     life
    -0.13
    POSITIVE LOGITS
     Effective
    0.16
    -effective
    0.16
     effectiveness
    0.14
    å¼±
    0.14
     EFFECT
    0.14
     strategy
    0.14
     Successful
    0.14
     effective
    0.14
    338
    0.14
    Effective
    0.14
    Act Density 0.370%

    No Known Activations