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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative events, particularly disasters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "disaster" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uli
    -0.72
    eters
    -0.71
    Ul
    -0.67
    Aim
    -0.67
    ta
    -0.66
     Packs
    -0.65
    Profile
    -0.64
    Ax
    -0.63
    arts
    -0.63
     Schiff
    -0.63
    POSITIVE LOGITS
     disaster
    3.71
     Disaster
    2.90
     disasters
    2.73
     catastrophe
    2.62
     calam
    1.96
     tragedy
    1.86
     catast
    1.80
     fiasco
    1.64
     debacle
    1.55
     crisis
    1.49
    Act Density 0.029%

    No Known Activations