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

    Neuronpedia

    INDEX
    Explanations

    names of states and their associations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     harc
    -0.15
    rey
    -0.15
    airro
    -0.14
    _RG
    -0.14
    Uno
    -0.14
    íĥĢìĿ´
    -0.13
    kke
    -0.13
    ãĥ©ãĤ¹
    -0.13
     Jerome
    -0.13
    urrent
    -0.13
    POSITIVE LOGITS
     State
    0.25
    å·ŀ
    0.25
     state
    0.24
    ans
    0.21
    state
    0.19
    -native
    0.19
    -based
    0.18
    (state
    0.18
    istan
    0.17
    -born
    0.17
    Act Density 0.159%

    No Known Activations