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

    Neuronpedia

    INDEX
    Explanations

    mentions of influence or influences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    influences by and of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     faſt
    -0.53
     preſent
    -0.53
    endphp
    -0.51
     leaſt
    -0.51
     ſtate
    -0.49
     ſmall
    -0.48
     greateſt
    -0.47
     ſta
    -0.47
     intest
    -0.46
     Houſe
    -0.46
    POSITIVE LOGITS
     influences
    0.89
    Influ
    0.88
     Influences
    0.85
    influenced
    0.84
     influenced
    0.82
     Influ
    0.75
     INFLU
    0.75
     inspirations
    0.75
     influ
    0.73
    influ
    0.71
    Act Density 0.008%

    No Known Activations