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

    Neuronpedia

    INDEX
    Explanations

    phrases related to distribution or dissemination of information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to restrictions on distribution or sharing of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gers
    -0.94
    isma
    -0.90
    bers
    -0.85
    friend
    -0.85
    izons
    -0.84
    ties
    -0.83
    stood
    -0.81
    keley
    -0.80
    gged
    -0.80
    zig
    -0.79
    POSITIVE LOGITS
     redistributed
    1.28
    CLASSIFIED
    0.80
     arrang
    0.76
     reprinted
    0.74
     generously
    0.74
     transcripts
    0.74
     redistribution
    0.74
    ONSORED
    0.73
    ricted
    0.73
     execut
    0.73
    Act Density 0.008%

    No Known Activations