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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals and their actions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ownership or possession, particularly in a personal or familial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confir
    -0.79
     pestic
    -0.66
    paren
    -0.65
     parentheses
    -0.64
     acknow
    -0.59
     obser
    -0.56
     therap
    -0.56
    VIDIA
    -0.56
     oblig
    -0.55
     sugg
    -0.55
    POSITIVE LOGITS
    selves
    1.00
    onto
    0.81
    heit
    0.80
    til
    0.78
    into
    0.77
     into
    0.76
     onto
    0.75
    Eva
    0.75
     accordingly
    0.73
    ById
    0.71
    Act Density 0.822%

    No Known Activations