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

    Neuronpedia

    INDEX
    Explanations

    phrases related to dependence or reliance on entities or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inez
    -0.17
    ither
    -0.16
    .au
    -0.15
    noc
    -0.15
    itez
    -0.15
    orp
    -0.15
    lement
    -0.14
    angelo
    -0.14
    resh
    -0.14
    izontally
    -0.14
    POSITIVE LOGITS
     heav
    0.33
     heavily
    0.31
     heavy
    0.31
     upon
    0.31
    heavy
    0.29
    Heavy
    0.28
     heavier
    0.28
     Heavy
    0.28
     Upon
    0.26
    Upon
    0.26
    Act Density 0.017%

    No Known Activations