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

    Neuronpedia

    INDEX
    Explanations

    the presence of the letters "sp" in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MetroFramework
    -0.15
    usters
    -0.15
    clipse
    -0.15
    usted
    -0.14
    ÛĮست
    -0.14
    campo
    -0.14
    YPE
    -0.14
    éł
    -0.13
    veis
    -0.13
    خت
    -0.13
    POSITIVE LOGITS
     sp
    0.36
     Sp
    0.28
    -sp
    0.26
    Sp
    0.24
    .Sp
    0.21
    /sp
    0.20
    sp
    0.19
    .sp
    0.18
     forth
    0.18
     spur
    0.17
    Act Density 0.017%

    No Known Activations