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

    Neuronpedia

    INDEX
    Explanations

    numbers related to casualties or injuries in various incidents

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to incidents involving casualties and injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffffcc
    -0.70
     Gutenberg
    -0.69
    sonian
    -0.68
    gemony
    -0.67
    ocracy
    -0.66
     philosophy
    -0.65
     Tyrann
    -0.64
     righteousness
    -0.63
     Advertisement
    -0.62
     semantics
    -0.62
    POSITIVE LOGITS
    ŃĶ
    0.81
     reportedly
    0.74
     crammed
    0.74
    Registered
    0.73
     already
    0.73
     allocated
    0.70
    assed
    0.69
    itialized
    0.69
    rolet
    0.69
    Ĥİ
    0.69
    Act Density 0.245%

    No Known Activations