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

    Neuronpedia

    INDEX
    Explanations

    references to humanitarian efforts or crises

    oai_token-act-pair · gpt-3.5-turbo

    terms related to humanitarian efforts and crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rams
    -0.83
    âĸ¬
    -0.72
    andals
    -0.68
    VP
    -0.67
    laus
    -0.66
     Tower
    -0.66
     Ran
    -0.65
    REE
    -0.64
     Ratt
    -0.64
    ###
    -0.64
    POSITIVE LOGITS
     humanitarian
    1.24
     labou
    0.96
     volunt
    0.94
     volunte
    0.87
     refugee
    0.86
     aid
    0.86
     laborers
    0.85
     convoy
    0.84
     orphans
    0.83
     ceasefire
    0.82
    Act Density 0.006%

    No Known Activations