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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to technical processes and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    анÑĤаж
    -0.15
    uckle
    -0.15
     dere
    -0.15
    ekte
    -0.15
    ocal
    -0.15
    ãĤĪãģŃ
    -0.14
     oc
    -0.14
    indow
    -0.14
    esh
    -0.14
     æ¨
    -0.14
    POSITIVE LOGITS
    ince
    0.15
    ENN
    0.15
    bond
    0.15
    LOCKS
    0.14
    affer
    0.14
    dre
    0.14
    æ°ij
    0.14
    essel
    0.14
     natur
    0.14
    unbind
    0.14
    Act Density 0.009%

    No Known Activations