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

    Neuronpedia

    INDEX
    Explanations

    phrases mentioning specific groups or organizations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve membership in a group or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nipples
    -0.74
     consistency
    -0.73
     nost
    -0.67
    ONSORED
    -0.65
     centerpiece
    -0.65
     distractions
    -0.64
     concess
    -0.64
     proportions
    -0.63
     references
    -0.62
     fumes
    -0.62
    POSITIVE LOGITS
     Parliament
    0.83
     parliament
    0.82
     Congress
    0.81
    odox
    0.80
     congress
    0.76
    errilla
    0.74
    amily
    0.71
     House
    0.69
     society
    0.68
    ãĥĦ
    0.67
    Act Density 0.087%

    No Known Activations