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

    Neuronpedia

    INDEX
    Explanations

    instances of interpersonal relationships and requests for communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imers
    -0.18
    imli
    -0.15
    oola
    -0.15
    лаÑĩ
    -0.14
    getMock
    -0.14
    SSIP
    -0.14
    fram
    -0.14
    viso
    -0.14
    zos
    -0.14
    orgia
    -0.14
    POSITIVE LOGITS
     whether
    0.28
     questions
    0.24
    whether
    0.23
     about
    0.22
    æĺ¯åIJ¦
    0.22
     how
    0.21
     why
    0.21
     Whether
    0.20
     question
    0.18
    questions
    0.18
    Act Density 0.043%

    No Known Activations