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

    Neuronpedia

    INDEX
    Explanations

    references to human experiences and emotions related to life and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aho
    -0.21
    akah
    -0.17
    ekl
    -0.15
     Hayward
    -0.15
    ови
    -0.15
    alace
    -0.14
    ảnh
    -0.14
    rip
    -0.14
    roken
    -0.13
    ationship
    -0.13
    POSITIVE LOGITS
     ourselves
    0.16
    ulle
    0.16
    uft
    0.15
    784
    0.14
    olle
    0.14
    /cpp
    0.14
    449
    0.14
    802
    0.14
     individually
    0.14
    chg
    0.14
    Act Density 0.266%

    No Known Activations