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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to global matters

    oai_token-act-pair · gpt-3.5-turbo

    references to "Global" and related organizational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.88
    ï¸
    -0.86
    INO
    -0.83
    IENT
    -0.83
    @#&
    -0.82
    sbm
    -0.81
    MENTS
    -0.80
    _-
    -0.79
    OULD
    -0.78
    avering
    -0.78
    POSITIVE LOGITS
     warming
    0.92
     Global
    0.84
     illumination
    0.82
     positioning
    0.77
    ization
    0.77
     ocean
    0.74
     terrorism
    0.74
     citizenship
    0.74
     imbalance
    0.72
     instability
    0.72
    Act Density 0.010%

    No Known Activations