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

    Neuronpedia

    INDEX
    Explanations

    sponsorship-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sponsorship and sponsorship-related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.83
     pend
    -0.76
     Shant
    -0.69
    otom
    -0.68
     pH
    -0.67
     Detective
    -0.67
     faults
    -0.67
     Pradesh
    -0.66
    EMS
    -0.65
     nerv
    -0.65
    POSITIVE LOGITS
    hips
    1.09
     sponsor
    0.95
    orship
    0.95
     sponsors
    0.95
     sponsorship
    0.91
     sponsoring
    0.90
     sponsored
    0.85
    Spons
    0.84
    paren
    0.77
    sponsored
    0.75
    Act Density 0.018%

    No Known Activations