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

    Neuronpedia

    INDEX
    Explanations

    references to the word "onto" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    en
    -0.81
    h
    -0.80
    o
    -0.75
    T
    -0.73
    in
    -0.72
    <em>
    -0.71
     thang
    -0.70
     h
    -0.69
    z
    -0.69
     tur
    -0.67
    POSITIVE LOGITS
     Theſe
    1.13
     doubtnut
    1.10
    Datuak
    1.08
     myſelf
    1.07
    ^(@)
    1.02
     itſelf
    1.01
     Portail
    1.01
     becauſe
    1.00
     niedersachsen
    1.00
     Monfieur
    0.99
    Act Density 0.057%

    No Known Activations