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

    Neuronpedia

    INDEX
    Explanations

    user mentions in social media or online platforms

    oai_token-act-pair · gpt-3.5-turbo

    references to blocking or unlocking digital content or accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     glim
    -0.75
     toget
    -0.71
     handc
    -0.70
    tti
    -0.67
     quarters
    -0.65
     Dh
    -0.63
     liner
    -0.61
     nutshell
    -0.60
    ppe
    -0.60
     Frie
    -0.59
    POSITIVE LOGITS
    able
    1.49
    ables
    1.42
    ABLE
    1.22
    ability
    1.21
    ment
    1.12
    abilities
    1.00
    ers
    0.96
    edIn
    0.95
    ible
    0.94
    er
    0.93
    Act Density 0.111%

    No Known Activations