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

    Neuronpedia

    INDEX
    Explanations

    phrases related to support and making a positive impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wax
    -0.17
    stor
    -0.16
     somewhat
    -0.15
    niž
    -0.15
    uplic
    -0.15
    ibles
    -0.14
    icher
    -0.14
    nger
    -0.14
     co
    -0.14
    mol
    -0.14
    POSITIVE LOGITS
     Difference
    0.18
     difference
    0.17
    heimer
    0.16
    difference
    0.16
    ifference
    0.16
    XE
    0.16
    Difference
    0.15
    ffect
    0.15
    unte
    0.15
    /change
    0.15
    Act Density 0.135%

    No Known Activations