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

    Neuronpedia

    INDEX
    Explanations

    instances where something belongs to or is related to someone or something

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to individual rights and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cery
    -0.77
     RHP
    -0.64
    actionDate
    -0.64
    trap
    -0.63
    ynes
    -0.63
    antam
    -0.62
    rehens
    -0.61
    both
    -0.58
    arnaev
    -0.58
    outheast
    -0.58
    POSITIVE LOGITS
    isms
    0.71
    izations
    0.70
     struggles
    0.69
     styles
    0.68
     preferences
    0.66
     ventures
    0.65
     selves
    0.63
    ologies
    0.61
    isations
    0.61
    iHUD
    0.61
    Act Density 0.186%

    No Known Activations