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

    Neuronpedia

    INDEX
    Explanations

    references to objects or subjects in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.76
    pozdrawiam
    -0.71
    bonjour
    -0.69
    odotus
    -0.67
    XmlAccessType
    -0.67
     LUMP
    -0.67
    Cordialement
    -0.67
    endphp
    -0.66
    voici
    -0.64
    mybatisplus
    -0.62
    POSITIVE LOGITS
     This
    1.54
     They
    1.52
     It
    1.51
     The
    1.35
     These
    1.33
    This
    1.29
     There
    1.29
    They
    1.23
    It
    1.22
     That
    1.21
    Act Density 0.459%

    No Known Activations