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

    Neuronpedia

    INDEX
    Explanations

    concerns related to safety and travel experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akis
    -0.15
     Fut
    -0.15
    öl
    -0.15
    à¸Ĭà¸Ļ
    -0.14
    fabs
    -0.14
     NSStringFromClass
    -0.14
     Fab
    -0.14
     smugg
    -0.13
     fabs
    -0.13
    amarin
    -0.13
    POSITIVE LOGITS
     safety
    0.44
     Safety
    0.41
    Safety
    0.38
    å®īåħ¨
    0.33
     security
    0.33
    afety
    0.33
     safer
    0.31
    security
    0.29
    -security
    0.29
     safe
    0.28
    Act Density 0.119%

    No Known Activations