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

    Neuronpedia

    INDEX
    Explanations

    phrases related to advocating for actions to be taken, often with a sense of urgency and importance

    oai_token-act-pair · gpt-3.5-turbo

    references to consistency or repetition of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leilan
    -0.69
    ospons
    -0.66
    urated
    -0.65
     Provides
    -0.64
    NULL
    -0.63
    andise
    -0.62
    osponsors
    -0.62
    opened
    -0.61
    usalem
    -0.59
    quished
    -0.59
    POSITIVE LOGITS
     same
    1.39
     unthinkable
    1.27
    same
    1.17
     opposite
    1.08
     simplest
    1.08
    oret
    1.03
     exact
    1.01
     utmost
    1.01
     hardest
    0.96
     groundwork
    0.95
    Act Density 0.075%

    No Known Activations