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

    Neuronpedia

    INDEX
    Explanations

    themes related to community engagement and kindness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IMS
    -0.17
    åĵŃ
    -0.15
    enga
    -0.14
    äºĨ解
    -0.14
     rov
    -0.14
    sti
    -0.13
     ФедеÑĢа
    -0.13
     mocks
    -0.13
    .GetProperty
    -0.13
    oog
    -0.13
    POSITIVE LOGITS
     Random
    0.32
     acts
    0.31
     random
    0.29
     Acts
    0.29
    Acts
    0.29
    Random
    0.28
     RANDOM
    0.27
    random
    0.25
     randomly
    0.25
     randomized
    0.24
    Act Density 0.026%

    No Known Activations