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

    Neuronpedia

    INDEX
    Explanations

    phrases where someone is convinced of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases focused on strong beliefs or convictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dos
    -0.72
    launch
    -0.70
    orrow
    -0.67
     Occupations
    -0.67
    regulated
    -0.66
    pmwiki
    -0.66
    umbn
    -0.64
    asks
    -0.63
    ember
    -0.63
    itage
    -0.63
    POSITIVE LOGITS
     convinced
    1.23
     persuaded
    1.00
     convince
    0.97
    -+-+
    0.92
     convin
    0.90
     persuade
    0.82
     lured
    0.79
    ãĥ¼ãĥĨ
    0.78
    ãĥ³ãĤ¸
    0.75
    rican
    0.73
    Act Density 0.011%

    No Known Activations