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

    Neuronpedia

    INDEX
    Explanations

    terms related to mental health education and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esk
    -0.16
    uib
    -0.16
    ìn
    -0.15
     synt
    -0.15
     Rehab
    -0.15
    Ø´Ùģ
    -0.14
     rehab
    -0.14
    Tube
    -0.14
    recision
    -0.13
    agnostics
    -0.13
    POSITIVE LOGITS
     safety
    0.29
     prevention
    0.27
     Safety
    0.27
     safer
    0.25
     Prevention
    0.24
     safe
    0.23
     Safe
    0.23
    Safety
    0.21
     awareness
    0.21
    safe
    0.20
    Act Density 0.181%

    No Known Activations