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

    Neuronpedia

    INDEX
    Explanations

    phrases related to learning or teaching concepts

    oai_token-act-pair · gpt-3.5-turbo

    educational or informative content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     respectively
    -0.60
    ]."
    -0.56
    $.
    -0.53
     ."
    -0.49
    ."[
    -0.47
    .</
    -0.46
     thereof
    -0.46
    )."
    -0.45
    +.
    -0.45
    .''
    -0.45
    POSITIVE LOGITS
    ':
    0.59
     Profile
    0.56
     Edit
    0.55
     FANTASY
    0.49
    ¶
    0.49
     Emails
    0.48
     Explan
    0.48
     Background
    0.48
     meanwhile
    0.48
    odore
    0.47
    Act Density 2.421%

    No Known Activations