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

    Neuronpedia

    INDEX
    Explanations

    words related to approval or acceptance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "welcomed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyomi
    -0.98
    negie
    -0.94
    iph
    -0.77
    aunder
    -0.76
    olester
    -0.75
    angler
    -0.73
    arcity
    -0.71
    pmwiki
    -0.70
    agnetic
    -0.70
    itect
    -0.69
    POSITIVE LOGITS
     welcome
    0.89
     welcomes
    0.86
     laughter
    0.81
     welcomed
    0.80
     welcoming
    0.78
     visitors
    0.76
    ï¸
    0.75
     aloud
    0.74
     UNHCR
    0.72
    ansen
    0.72
    Act Density 0.010%

    No Known Activations