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

    Neuronpedia

    INDEX
    Explanations

    terms related to financial matters and social issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to eligibility and criteria for benefits or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olerance
    -0.64
    gypt
    -0.63
    ournals
    -0.59
    ensions
    -0.59
    plom
    -0.58
    ogun
    -0.57
    ukong
    -0.56
    owered
    -0.56
    resy
    -0.55
    undown
    -0.55
    POSITIVE LOGITS
     è£ıè
    0.68
    !).
    0.63
     pree
    0.61
    ãĥ³ãĤ¸
    0.55
    ?).
    0.55
    !)
    0.55
     accounting
    0.54
    )."
    0.53
     phr
    0.53
     extras
    0.53
    Act Density 2.389%

    No Known Activations