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

    Neuronpedia

    INDEX
    Explanations

    verbs related to changing or modifying something significantly

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "alter" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĦ
    -0.78
    DragonMagazine
    -0.75
    ETF
    -0.73
    Bank
    -0.73
    Crunch
    -0.73
    PU
    -0.72
    fighter
    -0.72
    ARS
    -0.69
    Phones
    -0.68
    zzi
    -0.68
    POSITIVE LOGITS
     wrench
    0.88
     alters
    0.84
     havoc
    0.84
    ments
    0.83
     costumes
    0.80
     guiActiveUn
    0.80
    atile
    0.77
     ego
    0.77
    ives
    0.76
     alter
    0.76
    Act Density 0.017%

    No Known Activations