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

    Neuronpedia

    INDEX
    Explanations

    terms related to community engagement and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ój
    -0.15
    üs
    -0.15
    kl
    -0.15
    bsd
    -0.14
    LLU
    -0.14
    haus
    -0.14
    gress
    -0.14
    опиÑģ
    -0.14
    AGEMENT
    -0.14
     Painter
    -0.14
    POSITIVE LOGITS
     solo
    0.18
     Solo
    0.16
    uda
    0.16
     ladder
    0.15
     Ladies
    0.15
    iner
    0.15
    yna
    0.14
    Solo
    0.14
     unf
    0.14
    umm
    0.14
    Act Density 0.260%

    No Known Activations