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

    Neuronpedia

    INDEX
    Explanations

    social media related posts or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of posts and media in a social context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assies
    -0.78
    lees
    -0.73
     corridors
    -0.70
    atives
    -0.69
     fame
    -0.69
    verty
    -0.68
    rooms
    -0.68
    pees
    -0.68
    inations
    -0.67
    riages
    -0.66
    POSITIVE LOGITS
     spokesperson
    0.86
    ccording
    0.82
     researcher
    0.77
     example
    0.75
     spokeswoman
    0.74
     spokesman
    0.73
     stub
    0.73
     refres
    0.73
     biologist
    0.72
     therapist
    0.69
    Act Density 0.318%

    No Known Activations