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

    Neuronpedia

    INDEX
    Explanations

    words related to the action of releasing or being released

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "release" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iop
    -0.79
    isma
    -0.78
    baum
    -0.74
    aque
    -0.71
    anan
    -0.69
    asus
    -0.68
    Ń·
    -0.67
    alian
    -0.67
     Aj
    -0.66
    psc
    -0.66
    POSITIVE LOGITS
     valves
    0.88
    æĸ¹
    0.77
     valve
    0.74
     releasing
    0.73
    tion
    0.73
     RELEASE
    0.72
    tions
    0.72
    UGE
    0.67
    cha
    0.66
     Release
    0.66
    Act Density 0.031%

    No Known Activations