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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of being unmotivated or uninterested

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of being 'unmasked' or revealing identity, along with references to geological or structural layers like 'mantle.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    es
    -0.82
    uden
    -0.79
    vernment
    -0.78
    ombat
    -0.72
    itals
    -0.72
     Fighters
    -0.71
    eno
    -0.70
    scill
    -0.69
    ©¶æ
    -0.68
    estial
    -0.67
    POSITIVE LOGITS
     Peninsula
    0.83
    CLASSIFIED
    0.81
    ãĤ£
    0.76
    selves
    0.72
    akable
    0.70
     Leopard
    0.70
    asking
    0.69
    tub
    0.67
    otive
    0.67
    ware
    0.66
    Act Density 0.046%

    No Known Activations