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

    Neuronpedia

    INDEX
    Explanations

    phrases related to terrorism

    oai_token-act-pair · gpt-3.5-turbo

    references to terror-related events or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bye
    -0.69
    resso
    -0.68
     Quartz
    -0.66
    galitarian
    -0.64
    rovers
    -0.63
    Ģ
    -0.63
    flush
    -0.63
    Salt
    -0.63
    lease
    -0.61
     Rhod
    -0.59
    POSITIVE LOGITS
    istic
    1.04
    izing
    1.04
    fully
    1.02
    ization
    0.95
    ising
    0.88
    fulness
    0.87
    ophobic
    0.87
    ously
    0.87
    otropic
    0.87
    icious
    0.86
    Act Density 0.020%

    No Known Activations