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

    Neuronpedia

    INDEX
    Explanations

    words or phrases indicating an assumption or speculation

    oai_token-act-pair · gpt-3.5-turbo

    the word "presumably" and related terms indicating assumptions or speculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ament
    -0.75
    lv
    -0.73
    ger
    -0.70
    enko
    -0.68
    GER
    -0.67
    WOR
    -0.63
     Verd
    -0.63
    Eva
    -0.62
    ged
    -0.61
    java
    -0.61
    POSITIVE LOGITS
     accommod
    0.81
     reside
    0.75
     belonged
    0.74
     belong
    0.74
     situated
    0.74
     regenerate
    0.71
     housed
    0.71
     endowed
    0.71
     abolish
    0.71
     imitate
    0.71
    Act Density 0.027%

    No Known Activations