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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "release"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "release" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isma
    -0.72
    LI
    -0.63
    stal
    -0.63
    iop
    -0.63
     Vij
    -0.63
    aque
    -0.62
    cone
    -0.62
     Mania
    -0.60
    aces
    -0.57
    Gi
    -0.56
    POSITIVE LOGITS
    tion
    0.86
    ilts
    0.85
    æĸ¹
    0.82
    released
    0.76
    tions
    0.75
    Keys
    0.73
    éĹĺ
    0.71
     prisoners
    0.71
     valves
    0.70
     RELE
    0.70
    Act Density 0.054%

    No Known Activations