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

    Neuronpedia

    INDEX
    Explanations

    references to formal communications, such as letters, memos, and speeches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tics
    -0.71
    cause
    -0.71
    $.
    -0.66
    addons
    -0.63
    .''.
    -0.62
    upiter
    -0.62
    instead
    -0.61
    artifacts
    -0.61
    thumbnails
    -0.60
    animate
    -0.59
    POSITIVE LOGITS
     announcing
    0.83
     titled
    0.81
     interview
    0.81
     statement
    0.80
    idav
    0.80
     accompanying
    0.77
     nutshell
    0.75
     emailed
    0.74
     published
    0.74
     yesterday
    0.74
    Act Density 0.095%

    No Known Activations