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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities or subjects within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endencies
    -0.16
     personne
    -0.15
    对æĸ¹
    -0.15
    EndInit
    -0.15
    cano
    -0.15
    _DIP
    -0.15
     migrationBuilder
    -0.15
     __("
    -0.15
    ±ä¹IJ
    -0.14
    &eacute
    -0.14
    POSITIVE LOGITS
     couple
    0.46
     boys
    0.38
     pair
    0.35
     girls
    0.34
     family
    0.32
     trio
    0.32
     duo
    0.31
     gang
    0.29
     group
    0.28
     Couple
    0.28
    Act Density 0.264%

    No Known Activations