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

    Neuronpedia

    INDEX
    Explanations

    mentions of significant talent

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to talent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sole
    -0.68
    FACE
    -0.68
    soon
    -0.68
    than
    -0.66
    alone
    -0.63
    agher
    -0.62
    udge
    -0.62
     Mass
    -0.62
    nee
    -0.62
     PUR
    -0.62
    POSITIVE LOGITS
     talent
    1.30
     talents
    1.15
     Talent
    0.88
    anooga
    0.81
     eval
    0.78
    iuses
    0.75
    smanship
    0.74
     killers
    0.72
     performers
    0.71
     chops
    0.71
    Act Density 0.009%

    No Known Activations