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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating unexpected or surprising outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chal
    -0.18
    esModule
    -0.16
    emen
    -0.15
    undle
    -0.14
    osal
    -0.14
    ãĥ³ãĤ¹
    -0.14
     departure
    -0.13
    :title
    -0.13
    ohl
    -0.13
    деÑĢж
    -0.13
    POSITIVE LOGITS
     ended
    0.71
     ending
    0.68
     ends
    0.66
     Ended
    0.58
     Ending
    0.53
     wind
    0.53
     Ends
    0.52
     wound
    0.52
    Ended
    0.50
    ended
    0.49
    Act Density 0.229%

    No Known Activations