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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "common" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tring
    -0.17
    LM
    -0.16
    anager
    -0.16
    HK
    -0.15
    dued
    -0.14
    uations
    -0.14
    indi
    -0.14
    /ph
    -0.14
    gio
    -0.13
    cer
    -0.13
    POSITIVE LOGITS
    wealth
    0.27
    rijk
    0.18
    ridge
    0.17
    /common
    0.16
    akra
    0.15
    ies
    0.15
    est
    0.15
    sense
    0.14
    ality
    0.14
    itized
    0.14
    Act Density 0.022%

    No Known Activations