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

    Neuronpedia

    INDEX
    Explanations

    words associated with theft or illegal taking of something

    oai_token-act-pair · gpt-3.5-turbo

    the word "steal" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anamo
    -0.75
    band
    -0.74
    ichick
    -0.72
    bands
    -0.71
    present
    -0.71
    esa
    -0.67
    pora
    -0.66
    area
    -0.65
    lication
    -0.64
    rehens
    -0.64
    POSITIVE LOGITS
     glances
    0.94
     away
    0.81
     stolen
    0.79
    ster
    0.76
    weed
    0.76
     prey
    0.74
    sters
    0.69
     stealing
    0.66
     awa
    0.66
     revenge
    0.64
    Act Density 0.027%

    No Known Activations