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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating themes of reality and truth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĢł
    -0.15
     suddenly
    -0.15
     Winn
    -0.15
    rous
    -0.14
    elp
    -0.14
    orgia
    -0.14
    obe
    -0.14
     attention
    -0.14
     gratuite
    -0.14
    stanov
    -0.13
    POSITIVE LOGITS
     Demp
    0.17
    globals
    0.15
     playbook
    0.15
    .metro
    0.15
    .pitch
    0.14
    /pro
    0.14
    ivery
    0.13
    anya
    0.13
    ITU
    0.13
    zin
    0.13
    Act Density 0.085%

    No Known Activations