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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate attention and trust in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    steen
    -0.16
    assandra
    -0.14
    quist
    -0.14
    IODevice
    -0.14
    声
    -0.13
    upertino
    -0.13
    lut
    -0.13
    iyon
    -0.13
    ritch
    -0.13
    creen
    -0.13
    POSITIVE LOGITS
    akis
    0.15
    nict
    0.15
    ãĥ³ãĥķ
    0.15
    robe
    0.15
     Stub
    0.14
    anja
    0.14
    anch
    0.14
    ola
    0.14
    åĮ
    0.14
    enders
    0.14
    Act Density 0.103%

    No Known Activations