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

    Neuronpedia

    INDEX
    Explanations

    adjectives relating to characteristics such as appearance, personality, or affiliations

    oai_token-act-pair · gpt-3.5-turbo

    attributes related to characteristics or qualities of individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onement
    -0.81
    xtap
    -0.76
    forcer
    -0.75
    hander
    -0.75
    wark
    -0.74
    hirt
    -0.71
    jam
    -0.70
    vention
    -0.69
    heon
    -0.68
    hemoth
    -0.68
    POSITIVE LOGITS
     agendas
    1.39
     backgrounds
    1.39
     histories
    1.35
     intentions
    1.35
     aspirations
    1.34
     ambitions
    1.34
     tendencies
    1.24
     sensibilities
    1.24
     motives
    1.22
     personalities
    1.21
    Act Density 0.219%

    No Known Activations