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

    Neuronpedia

    INDEX
    Explanations

    names of people, particularly those with titles or roles such as "chef" or "director"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specialized equipment or roles in situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    encies
    -0.72
    INESS
    -0.72
    ACY
    -0.68
    ELY
    -0.64
     âľĵ
    -0.64
     convergence
    -0.64
    utenberg
    -0.63
    duino
    -0.63
    ãĤ£
    -0.62
     bombshell
    -0.61
    POSITIVE LOGITS
    ffe
    0.90
    arers
    0.83
    rolet
    0.78
    razil
    0.78
    gow
    0.73
    iatric
    0.72
    illac
    0.68
    vised
    0.68
    ferred
    0.68
    irst
    0.67
    Act Density 0.069%

    No Known Activations