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

    Neuronpedia

    INDEX
    Explanations

    instances of job or application-related contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "applied for" along with related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ofi
    -0.75
    hen
    -0.74
    beard
    -0.73
    respect
    -0.73
    velt
    -0.72
    pod
    -0.72
    mith
    -0.70
    Pod
    -0.70
    heim
    -0.67
    gaard
    -0.67
    POSITIVE LOGITS
     waivers
    0.85
     lottery
    0.81
     registration
    0.78
     citizenship
    0.77
     renewal
    0.77
     waiver
    0.77
     parole
    0.76
     eligibility
    0.74
     volunte
    0.74
     exting
    0.72
    Act Density 0.050%

    No Known Activations