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

    Neuronpedia

    INDEX
    Explanations

    phrases related to global initiatives and studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    th
    -0.16
    rick
    -0.15
    147
    -0.15
    ud
    -0.15
     TABLE
    -0.15
     Florian
    -0.14
    ater
    -0.14
    bel
    -0.14
     touched
    -0.14
    ck
    -0.14
    POSITIVE LOGITS
     guide
    0.24
     tale
    0.23
     primer
    0.22
    -guide
    0.20
     Guide
    0.19
     Primer
    0.19
    uide
    0.19
    ailable
    0.18
    guide
    0.17
    outu
    0.17
    Act Density 0.071%

    No Known Activations