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

    Neuronpedia

    INDEX
    Explanations

    elements of community and social interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appa
    -0.18
    igner
    -0.15
    ouz
    -0.15
     Permanent
    -0.15
    burg
    -0.15
    Ðĥ
    -0.15
     sn
    -0.14
    izu
    -0.14
     Tong
    -0.14
     hope
    -0.14
    POSITIVE LOGITS
    oken
    0.21
    lessness
    0.19
    lessly
    0.18
    åľŃ
    0.16
    less
    0.16
    alnız
    0.15
    ernetes
    0.15
    eded
    0.15
    ORMAT
    0.15
     Pods
    0.15
    Act Density 1.186%

    No Known Activations