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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scientific processes or technical actions

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to evidence and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ?)
    -1.02
    )?
    -0.99
    ?]
    -0.88
    ?),
    -0.82
    ?)
    -0.82
    ?",
    -0.77
    "?
    -0.75
    ?).
    -0.74
    ?ãĢį
    -0.73
    ?'
    -0.71
    POSITIVE LOGITS
    .
    0.69
     revealing
    0.66
     allowing
    0.64
     indicating
    0.64
     demonstrating
    0.60
     informing
    0.59
     whereby
    0.59
     ensuring
    0.58
     overshadow
    0.57
     totaling
    0.57
    Act Density 1.376%

    No Known Activations