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

    Neuronpedia

    INDEX
    Explanations

    references to media and journalism, particularly in the context of censorship and press credentials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igel
    -0.16
    μι
    -0.15
    cury
    -0.14
    opoulos
    -0.14
     —
    -0.14
     Mrs
    -0.13
    ampus
    -0.13
    autos
    -0.13
     accidentally
    -0.13
    ziej
    -0.13
    POSITIVE LOGITS
     CP
    0.32
    CP
    0.28
    -CP
    0.24
     cp
    0.23
    .cp
    0.23
    _CP
    0.22
    (cp
    0.22
    _cp
    0.22
    ,cp
    0.22
    cp
    0.21
    Act Density 0.002%

    No Known Activations