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

    Neuronpedia

    INDEX
    Explanations

    phrases related to business deals

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to agreements and contracts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sylv
    -0.74
    enes
    -0.72
    rosse
    -0.71
    phia
    -0.69
     rays
    -0.67
    eh
    -0.66
    Sense
    -0.66
    athi
    -0.66
     epile
    -0.66
    kie
    -0.65
    POSITIVE LOGITS
     whereby
    0.96
     overseen
    0.89
     guaranteeing
    0.86
     negotiated
    0.84
     ratified
    0.84
     approvals
    0.82
     agreements
    0.78
     guarant
    0.77
     guaranteed
    0.77
     authorised
    0.76
    Act Density 0.453%

    No Known Activations