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

    Neuronpedia

    INDEX
    Explanations

    non-zero symbols or mathematical operations in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bigoplus
    -0.89
     Curtis
    -0.84
    triangleq
    -0.76
    Longrightarrow
    -0.74
    adpleegd
    -0.73
    InputBorder
    -0.71
    исленность
    -0.71
    Curtis
    -0.69
    Gue
    -0.69
    triangleright
    -0.68
    POSITIVE LOGITS
     \
    1.29
    ;\
    0.91
    '\
    0.90
    \
    0.89
    "\
    0.88
    !\
    0.84
    ))\
    0.84
    NonQuery
    0.82
     "\
    0.82
    >\
    0.82
    Act Density 0.466%

    No Known Activations