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

    Neuronpedia

    INDEX
    Explanations

    elements related to relationships and emotional connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.58
    loài
    -0.54
     चीज़ों
    -0.51
    ValueGeneration
    -0.50
    ніципа
    -0.50
     Infórmanos
    -0.50
     typelib
    -0.48
    IsContent
    -0.47
    CompilerServices
    -0.47
    jMenuItem
    -0.46
    POSITIVE LOGITS
     failed
    0.94
     FAILED
    0.83
     insufficient
    0.83
     fail
    0.83
     failing
    0.82
     deficient
    0.78
     fails
    0.77
    Failed
    0.77
     FAIL
    0.75
     poorly
    0.75
    Act Density 0.904%

    No Known Activations