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

    Neuronpedia

    INDEX
    Explanations

    instructions related to signing up for newsletters or continuing to read a story

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscribing or signing up for newsletters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynt
    -0.82
    ynthesis
    -0.81
    aimon
    -0.74
    anca
    -0.73
    abal
    -0.70
    tten
    -0.68
    afety
    -0.66
     hurd
    -0.65
    hend
    -0.63
    mons
    -0.62
    POSITIVE LOGITS
     Password
    0.72
     unlocks
    0.67
     guiActive
    0.67
     toile
    0.67
    iframe
    0.67
    ideshow
    0.66
    ãģį
    0.66
    OTUS
    0.66
    ername
    0.65
    ATOR
    0.64
    Act Density 0.038%

    No Known Activations