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

    Neuronpedia

    INDEX
    Explanations

    terms related to communication and language skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĪ
    -0.15
    ajan
    -0.14
    odoxy
    -0.14
    Detach
    -0.13
    Disallow
    -0.13
    ÑĪиб
    -0.13
    /tos
    -0.13
    _EXEC
    -0.13
     incentiv
    -0.13
    annel
    -0.12
    POSITIVE LOGITS
     Students
    0.18
     literal
    0.18
     grade
    0.18
     compare
    0.17
     text
    0.17
     Grade
    0.17
    Literal
    0.17
     texts
    0.17
     textual
    0.16
    literal
    0.16
    Act Density 0.033%

    No Known Activations