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

    Neuronpedia

    INDEX
    Explanations

    code syntax and structure in programming language contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Życiorys
    -0.64
    ondissement
    -0.63
     firm
    -0.49
    tober
    -0.46
     Réseau
    -0.45
    Према
    -0.45
    pecia
    -0.44
     Administrativna
    -0.43
    Ϣ
    -0.43
    ortment
    -0.43
    POSITIVE LOGITS
    ransition
    0.78
    arget
    0.68
    ypes
    0.66
    rans
    0.64
    rigger
    0.63
    imes
    0.63
    unnel
    0.62
    extAlignment
    0.61
    witter
    0.60
    FunctionFlags
    0.60
    Act Density 0.532%

    No Known Activations