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

    Neuronpedia

    INDEX
    Explanations

    instances where "like" is used to indicate similarity or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    borg
    -0.20
    tol
    -0.15
    ł
    -0.14
    -flat
    -0.13
    otropic
    -0.13
    sett
    -0.13
     Yük
    -0.13
    eyer
    -0.13
     Ingredients
    -0.13
    etsk
    -0.13
    POSITIVE LOGITS
     Nack
    0.17
     Danh
    0.16
    antee
    0.15
    ONTAL
    0.15
     Dudley
    0.15
    OID
    0.15
    anta
    0.15
    ystone
    0.14
    ilm
    0.14
    yst
    0.14
    Act Density 0.000%

    No Known Activations