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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "visit" or its variations, such as "visiting" or "visited"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "visit" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tackle
    -0.63
    ģĸ
    -0.63
    starter
    -0.61
     wiser
    -0.60
    rd
    -0.60
    raught
    -0.59
    riad
    -0.59
     Carnegie
    -0.59
    tons
    -0.59
     bare
    -0.59
    POSITIVE LOGITS
    ibility
    1.25
    itor
    1.11
    itors
    1.11
    cer
    1.01
    ibly
    1.00
    UAL
    0.98
    apore
    0.94
    vim
    0.94
    ipers
    0.90
    ually
    0.90
    Act Density 0.029%

    No Known Activations