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

    Neuronpedia

    INDEX
    Explanations

    phrases related to event attendees or participants

    oai_token-act-pair · gpt-3.5-turbo

    terms related to individuals attending events or gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ANN
    -0.74
     Li
    -0.66
    NESS
    -0.66
     Neural
    -0.65
    Fel
    -0.65
     Cay
    -0.65
    ayne
    -0.65
     framework
    -0.64
    yz
    -0.63
     Agenda
    -0.63
    POSITIVE LOGITS
    ffiti
    0.96
    veyard
    0.92
    etheless
    0.86
    pread
    0.85
    hesive
    0.78
    ipop
    0.77
    rehend
    0.77
    rontal
    0.76
    atoon
    0.75
    velength
    0.75
    Act Density 0.016%

    No Known Activations