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

    Neuronpedia

    INDEX
    Explanations

    references to educational programs and initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ium
    -0.15
    stride
    -0.15
     anc
    -0.15
     ignite
    -0.14
     coverage
    -0.14
    rub
    -0.14
    bia
    -0.13
    idon
    -0.13
    ngthen
    -0.13
    edere
    -0.13
    POSITIVE LOGITS
     involves
    0.35
     involve
    0.32
     involved
    0.31
     involving
    0.28
     consists
    0.23
     invol
    0.23
    æ¶ī
    0.23
     aims
    0.21
     consist
    0.21
     aim
    0.21
    Act Density 0.252%

    No Known Activations