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

    Neuronpedia

    INDEX
    Explanations

    the presence of organizational and collaborative language within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AS
    -0.16
     CE
    -0.16
    odem
    -0.16
    INCLUDING
    -0.15
     BCE
    -0.15
     CSL
    -0.15
     AE
    -0.15
    enne
    -0.15
     UP
    -0.14
     AT
    -0.14
    POSITIVE LOGITS
     MART
    0.22
     JACK
    0.22
     VAL
    0.21
     LIN
    0.21
     LORD
    0.21
     MAC
    0.20
     CHAR
    0.20
     CAM
    0.20
     PARK
    0.20
     LANG
    0.20
    Act Density 0.112%

    No Known Activations