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

    Neuronpedia

    INDEX
    Explanations

    sections of text marked with a specific symbol sequence

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant numerical values or counts related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.82
    nesday
    -0.80
     describ
    -0.78
    ©¶æ
    -0.75
     neighb
    -0.72
     carving
    -0.71
     agre
    -0.70
     himself
    -0.67
     compr
    -0.67
     nightly
    -0.67
    POSITIVE LOGITS
    Reviewer
    1.26
    Advertisements
    1.16
    Advertisement
    1.13
    If
    1.12
    Whether
    1.10
    Copyright
    1.09
    Published
    1.08
    This
    1.08
    Contents
    1.08
    Contribut
    1.08
    Act Density 0.521%

    No Known Activations