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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols commonly used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MEM
    -0.14
    erno
    -0.13
    å»
    -0.13
    WithOptions
    -0.13
     pueblo
    -0.13
    ninger
    -0.12
    /rss
    -0.12
     PEM
    -0.12
    PBS
    -0.12
    commons
    -0.12
    POSITIVE LOGITS
     hackers
    0.27
     hacking
    0.26
     cybersecurity
    0.25
     hacker
    0.25
    hack
    0.24
     hacked
    0.24
     hack
    0.24
     Oct
    0.23
     breached
    0.23
     breach
    0.21
    Act Density 0.004%

    No Known Activations