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

    Neuronpedia

    INDEX
    Explanations

    instances of significant events or accidents involving injuries and law enforcement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.82
     Cree
    -0.70
    BLIC
    -0.64
     Polk
    -0.63
     Cotton
    -0.63
     Ces
    -0.62
     BCC
    -0.60
     Mock
    -0.60
    ï¸ı
    -0.59
     brass
    -0.59
    POSITIVE LOGITS
    saving
    1.29
    cycle
    1.26
    cycles
    1.13
    sized
    1.12
    span
    1.06
    changing
    1.05
    wreck
    1.04
    loving
    1.01
    consuming
    1.01
    eating
    0.99
    Act Density 0.039%

    No Known Activations