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

    Neuronpedia

    INDEX
    Explanations

    words related to eligibility for benefits or services

    oai_token-act-pair · gpt-3.5-turbo

    terms related to eligibility for programs or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ijk
    -0.81
    Else
    -0.67
    SO
    -0.67
    helle
    -0.66
    ERN
    -0.65
    pread
    -0.64
    hed
    -0.62
    aster
    -0.62
    rough
    -0.61
    ween
    -0.60
    POSITIVE LOGITS
    untarily
    0.94
    iaries
    0.79
    iciary
    0.76
    ansas
    0.75
    Reviewer
    0.75
     qualify
    0.74
    iary
    0.73
    itably
    0.73
     disqualified
    0.73
     disqual
    0.72
    Act Density 0.023%

    No Known Activations