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

    Neuronpedia

    INDEX
    Explanations

    words related to dependency or dependence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dependency and interdependence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ific
    -0.80
    shr
    -0.77
    tell
    -0.75
    ²¾
    -0.74
    mberg
    -0.74
    furt
    -0.74
    Ĥ¬
    -0.74
    itz
    -0.73
    efer
    -0.73
    wagen
    -0.72
    POSITIVE LOGITS
    encies
    1.09
    ency
    0.89
     dependency
    0.79
     upon
    0.78
    doms
    0.77
     cripp
    0.72
     Kingdoms
    0.70
     injection
    0.68
    enza
    0.68
     strain
    0.67
    Act Density 0.045%

    No Known Activations