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

    Neuronpedia

    INDEX
    Explanations

    verbs related to interference or meddling

    oai_token-act-pair · gpt-3.5-turbo

    terms related to interference or meddling in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    borne
    -0.70
    itan
    -0.68
     flies
    -0.67
    corn
    -0.62
    mail
    -0.60
    phies
    -0.58
    marked
    -0.57
     Palo
    -0.57
    vation
    -0.55
     Marin
    -0.54
    POSITIVE LOGITS
     extensively
    1.03
     peacefully
    0.99
     violently
    0.98
     withd
    0.96
     positively
    0.93
     heavily
    0.92
     negatively
    0.91
     territ
    0.90
     forcefully
    0.89
     strongly
    0.89
    Act Density 0.184%

    No Known Activations