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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and statements of opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.81
     betweenstory
    -0.81
    Datuak
    -0.72
    writeFieldEnd
    -0.70
    جغرافيا
    -0.69
    \{\\
    -0.66
     disponibilités
    -0.66
     Мексичка
    -0.66
    outons
    -0.65
    GrantedAuthority
    -0.64
    POSITIVE LOGITS
     onBind
    0.48
     heure
    0.47
     I
    0.46
    ❉
    0.44
    Monta
    0.44
     conjecture
    0.43
    ArgumentParser
    0.42
     espec
    0.42
    ığ
    0.41
    keyboard
    0.41
    Act Density 0.313%

    No Known Activations