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

    Neuronpedia

    INDEX
    Explanations

    patterns or sequences of code blocks and their organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Balo
    -0.52
    ان
    -0.51
    an
    -0.49
     large
    -0.49
    ESTAMP
    -0.48
     Lazar
    -0.47
     Teo
    -0.46
    on
    -0.44
    Ane
    -0.44
     Lop
    -0.44
    POSITIVE LOGITS
     Gallimard
    0.62
     Personne
    0.60
     banget
    0.58
     argint
    0.57
    0.57
     Pues
    0.57
    Personne
    0.57
     poquito
    0.56
    ########.
    0.55
     Jurí
    0.55
    Act Density 0.305%

    No Known Activations