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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions of decreasing or minimizing something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reduction or minimizing of various factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    place
    -0.64
    Bet
    -0.60
    finished
    -0.59
    atom
    -0.59
    spr
    -0.58
    ansas
    -0.58
    new
    -0.58
    Found
    -0.58
    REL
    -0.58
    feld
    -0.57
    POSITIVE LOGITS
     inhib
    0.89
     visibility
    0.83
     friction
    0.82
     effectiveness
    0.81
     reliance
    0.81
     workload
    0.79
     emissions
    0.79
    icides
    0.78
     likelihood
    0.76
    ahime
    0.75
    Act Density 0.055%

    No Known Activations