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

    Neuronpedia

    INDEX
    Explanations

    phrases related to judgments and decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal and ethical judgments or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    >)
    -0.80
    ?),
    -0.68
    ggles
    -0.62
    )\
    -0.60
    )</
    -0.59
    =#
    -0.57
    ?'
    -0.57
    racuse
    -0.55
    âĢIJ
    -0.55
     hilar
    -0.54
    POSITIVE LOGITS
     because
    1.21
     but
    0.98
    because
    0.92
     although
    0.89
     owing
    0.88
     "...
    0.88
     despite
    0.88
     "
    0.83
    .
    0.83
     ''
    0.82
    Act Density 0.955%

    No Known Activations