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

    Neuronpedia

    INDEX
    Explanations

    terms related to data retention and privacy concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ologue
    -0.73
     Qatar
    -0.70
    ologies
    -0.70
    olog
    -0.70
    Ô
    -0.69
    externalActionCode
    -0.65
     Cosponsors
    -0.65
    OLOG
    -0.62
     Billion
    -0.62
    ELF
    -0.62
    POSITIVE LOGITS
    ability
    0.81
     retention
    0.79
    ment
    0.77
    ministic
    0.76
    ency
    0.74
    ary
    0.73
    ees
    0.72
    luster
    0.70
    dated
    0.70
    omore
    0.70
    Act Density 0.010%

    No Known Activations