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

    Neuronpedia

    INDEX
    Explanations

    references to authors or contributors in academic or research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    λια
    -0.15
    984
    -0.14
    led
    -0.14
    .Schema
    -0.14
    ÏĢη
    -0.14
    heit
    -0.14
    EP
    -0.13
    üny
    -0.13
    odox
    -0.13
    _TRAIN
    -0.13
    POSITIVE LOGITS
    thew
    0.24
    ernal
    0.23
    ÄĽj
    0.22
    ematic
    0.21
    ieu
    0.20
    imeo
    0.20
    ias
    0.20
    rex
    0.20
    uration
    0.19
    inee
    0.19
    Act Density 0.050%

    No Known Activations