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

    Neuronpedia

    INDEX
    Explanations

    phrases related to problem-solving or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to surveillance and user control in systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Originally
    -0.61
    ocry
    -0.51
     refers
    -0.49
     denotes
    -0.47
     Edited
    -0.46
     Nobel
    -0.45
     consists
    -0.45
     puzzled
    -0.44
     summed
    -0.44
     Variant
    -0.44
    POSITIVE LOGITS
    )).
    0.84
    ]."
    0.79
    %.
    0.78
    '."
    0.74
    '.
    0.74
    .'"
    0.72
    .''.
    0.71
    ]).
    0.70
    .).
    0.68
    ".
    0.66
    Act Density 3.587%

    No Known Activations