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

    Neuronpedia

    INDEX
    Explanations

    phrases related to safety

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orno
    -0.78
    yi
    -0.76
    iry
    -0.74
    agents
    -0.69
     betrayal
    -0.68
    amy
    -0.67
     crime
    -0.66
    oras
    -0.65
    plates
    -0.65
    lins
    -0.64
    POSITIVE LOGITS
     exting
    0.97
     safely
    0.96
     conclud
    0.95
     outweigh
    0.81
     evacuated
    0.80
    ufact
    0.79
    veland
    0.76
    ãĤ©
    0.75
     transitioned
    0.75
     detonated
    0.75
    Act Density 0.012%

    No Known Activations