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

    Neuronpedia

    INDEX
    Explanations

    new or recent developments or events

    oai_token-act-pair · gpt-3.5-turbo

    references to newness or recent developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    someone
    -0.69
    something
    -0.65
    rarily
    -0.65
    nant
    -0.65
     fert
    -0.64
    esson
    -0.64
     uphold
    -0.64
    plin
    -0.62
    ainers
    -0.62
    rats
    -0.62
    POSITIVE LOGITS
     foray
    0.91
     inaugural
    0.87
     selves
    0.87
     birthday
    0.84
     cousin
    0.81
     reputation
    0.80
     contribution
    0.78
    eworld
    0.77
     demise
    0.77
     agenda
    0.76
    Act Density 0.354%

    No Known Activations