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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate connections or relationships between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aux
    -0.16
    êu
    -0.14
    argent
    -0.14
    ãĥ§
    -0.14
    Õ¡
    -0.13
    ester
    -0.13
     vyz
    -0.13
    alker
    -0.13
    lesen
    -0.13
     $?
    -0.13
    POSITIVE LOGITS
     former
    0.21
     erst
    0.21
     member
    0.20
    atio
    0.17
     one
    0.17
     part
    0.17
     owner
    0.17
     frequent
    0.15
     co
    0.15
     friend
    0.15
    Act Density 0.045%

    No Known Activations