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

    Neuronpedia

    INDEX
    Explanations

    terms related to subscriptions or selections

    oai_token-act-pair · gpt-3.5-turbo

    directives related to user input and selections for subscriptions and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imer
    -0.82
    emies
    -0.73
    matter
    -0.70
    enz
    -0.64
    seek
    -0.62
    auld
    -0.62
    aroo
    -0.62
    worth
    -0.62
    geist
    -0.61
    usher
    -0.61
    POSITIVE LOGITS
    \<
    0.80
     Cancel
    0.77
    ause
    0.73
     Submit
    0.67
    Export
    0.67
     manually
    0.65
    ornia
    0.64
     FIGHT
    0.63
     comma
    0.63
     REG
    0.62
    Act Density 0.046%

    No Known Activations