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

    Neuronpedia

    INDEX
    Explanations

    aspects related to journalistic integrity and freedom of speech issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acas
    -0.15
    ladu
    -0.14
    ousse
    -0.14
     Middleton
    -0.14
    _FM
    -0.14
    ecer
    -0.14
    .desktop
    -0.14
    OUCH
    -0.14
    OAD
    -0.13
     éĸ¢éĢ£
    -0.13
    POSITIVE LOGITS
    thing
    0.15
     slow
    0.15
    hang
    0.15
    acher
    0.15
     seasonal
    0.14
    æĮ¯ãĤĬ
    0.14
    appy
    0.14
    abet
    0.14
     Un
    0.14
    420
    0.13
    Act Density 0.051%

    No Known Activations