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

    Neuronpedia

    INDEX
    Explanations

    phrases containing personal titles such as "Dr." along with names

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or persona

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulative
    -0.55
    ependent
    -0.55
    staking
    -0.54
    cipled
    -0.53
    utenberg
    -0.50
    ":[{"
    -0.50
    matical
    -0.49
     Kejriwal
    -0.49
    untled
    -0.49
     varied
    -0.48
    POSITIVE LOGITS
    .).
    0.67
    .''
    0.63
    ensis
    0.59
    *.
    0.58
    ".
    0.58
    '.
    0.57
    ''.
    0.55
    iani
    0.55
    .</
    0.55
    %.
    0.52
    Act Density 2.507%

    No Known Activations