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

    Neuronpedia

    INDEX
    Explanations

    words associated with actions and processes, particularly those that imply judgment or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itra
    -0.17
    ismus
    -0.14
    âĶĢ
    -0.14
    ubber
    -0.14
    lsa
    -0.14
    ubic
    -0.14
    isp
    -0.13
    endas
    -0.13
    ems
    -0.13
    æŃ
    -0.13
    POSITIVE LOGITS
    oft
    0.15
    ocha
    0.15
    askell
    0.15
    assen
    0.14
    fony
    0.14
    .nt
    0.14
    CID
    0.14
     Salisbury
    0.14
     Hale
    0.14
    esco
    0.14
    Act Density 0.002%

    No Known Activations