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

    Neuronpedia

    INDEX
    Explanations

    terms related to distinctiveness and differentiation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icina
    -0.17
     hang
    -0.17
    hang
    -0.16
    iche
    -0.16
    reu
    -0.15
    stab
    -0.15
    esus
    -0.15
    ettel
    -0.14
    erland
    -0.14
    »
    -0.14
    POSITIVE LOGITS
    ively
    0.26
    iveness
    0.19
    ially
    0.18
    ily
    0.17
    ;y
    0.16
    aland
    0.15
    RN
    0.15
    ÌĨ
    0.15
    unnel
    0.15
    zeitig
    0.14
    Act Density 0.016%

    No Known Activations