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

    Neuronpedia

    INDEX
    Explanations

    words related to extreme negative experiences or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĿ¡
    -0.15
    ynamo
    -0.15
    oren
    -0.15
    .XR
    -0.15
    immers
    -0.14
    yah
    -0.14
     AssemblyVersion
    -0.14
    orne
    -0.14
    elsey
    -0.14
    vest
    -0.13
    POSITIVE LOGITS
    kova
    0.17
    нова
    0.15
    нев
    0.15
    ä¸Ģä¸ĭ
    0.14
    å§Ĩ
    0.14
    rack
    0.13
    quan
    0.13
    .Concurrent
    0.13
    ertino
    0.13
    fork
    0.13
    Act Density 0.080%

    No Known Activations