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

    Neuronpedia

    INDEX
    Explanations

    words related to the impact of events, decisions, or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of impact or effects on various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Begin
    -0.70
     sweats
    -0.62
     Forbidden
    -0.62
    ft
    -0.61
    Fail
    -0.61
    gart
    -0.60
     Hedge
    -0.60
     Sins
    -0.59
    cknowled
    -0.59
     Bugs
    -0.58
    POSITIVE LOGITS
     impacting
    0.90
     reverber
    0.89
     affecting
    0.87
     impact
    0.86
     impacts
    0.85
     multiplier
    0.85
     ripple
    0.83
    bringer
    0.82
    ful
    0.80
     havoc
    0.80
    Act Density 0.087%

    No Known Activations