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

    Neuronpedia

    INDEX
    Explanations

    websites and web-related terms

    oai_token-act-pair · gpt-3.5-turbo

    URLs and domain names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     grounding
    -0.76
     divide
    -0.76
     recess
    -0.75
     snipers
    -0.75
     accent
    -0.75
     subordinate
    -0.74
     rooting
    -0.73
     conflicting
    -0.71
     marked
    -0.71
     setback
    -0.71
    POSITIVE LOGITS
    wordpress
    1.87
    blogspot
    1.87
    com
    1.79
    org
    1.72
    info
    1.55
    net
    1.53
    tumblr
    1.53
    yahoo
    1.33
    exe
    1.31
    files
    1.31
    Act Density 0.094%

    No Known Activations