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

    Neuronpedia

    INDEX
    Explanations

    references to specific organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ex
    -0.25
    ts
    -0.24
    et
    -0.23
    hen
    -0.22
    um
    -0.22
    h
    -0.21
    hd
    -0.21
    п
    -0.21
    hist
    -0.20
    hes
    -0.20
    POSITIVE LOGITS
    cribe
    0.19
    RS
    0.18
    weeney
    0.18
    dio
    0.16
    rp
    0.16
    rw
    0.16
    aan
    0.16
    cribed
    0.16
    rq
    0.15
    cribing
    0.15
    Act Density 0.105%

    No Known Activations