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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cover-ups or concealment of information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to cover-ups and concealment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agonist
    -0.76
    ranch
    -0.74
    Fan
    -0.73
    join
    -0.72
    anian
    -0.70
    joining
    -0.67
    aghan
    -0.67
    quad
    -0.66
    nir
    -0.65
    gob
    -0.65
    POSITIVE LOGITS
     scandals
    0.77
     allegations
    0.76
     accusations
    0.75
     crimes
    0.73
     affair
    0.72
     wrongdoing
    0.71
     fals
    0.70
     perpet
    0.70
     proceedings
    0.69
     investigations
    0.68
    Act Density 0.041%

    No Known Activations