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

    Neuronpedia

    INDEX
    Explanations

    words related to destruction or negative outcomes

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to destinations and destruction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.76
    interstitial
    -0.75
    culosis
    -0.71
    SPONSORED
    -0.64
    Reviewer
    -0.62
     concessions
    -0.62
    esome
    -0.60
     easing
    -0.60
     timestamp
    -0.60
     denomin
    -0.60
    POSITIVE LOGITS
    ruct
    1.27
    roying
    1.25
    itute
    1.17
    ination
    1.09
    rip
    1.05
    inations
    1.05
    ruction
    1.02
    ined
    1.01
    ript
    0.99
    ãĥ´
    0.99
    Act Density 0.014%

    No Known Activations