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

    Neuronpedia

    INDEX
    Explanations

    themes related to unexpected outcomes and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chal
    -0.19
    :title
    -0.16
    esModule
    -0.15
    osal
    -0.14
    avenport
    -0.14
    èļ
    -0.14
     departure
    -0.14
    intl
    -0.13
    esser
    -0.13
    orry
    -0.13
    POSITIVE LOGITS
     ended
    0.68
     ending
    0.65
     ends
    0.65
     Ended
    0.57
     wind
    0.54
     Ending
    0.52
     Ends
    0.52
     wound
    0.52
     winding
    0.49
    Ended
    0.48
    Act Density 0.206%

    No Known Activations