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

    Neuronpedia

    INDEX
    Explanations

    words related to significant effects or influences

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of impact in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IDES
    -0.67
     pitches
    -0.61
     Begin
    -0.60
     drafts
    -0.60
     confession
    -0.59
     Sins
    -0.58
     Dong
    -0.56
     Alps
    -0.56
     dumps
    -0.56
     Investigation
    -0.55
    POSITIVE LOGITS
    notations
    0.90
    notation
    0.88
     reverber
    0.88
     ripple
    0.76
     multiplier
    0.75
     impacts
    0.75
     impact
    0.74
     impacting
    0.74
     adversely
    0.72
     affecting
    0.72
    Act Density 0.073%

    No Known Activations