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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating levels of engagement or involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oad
    -0.16
    apa
    -0.15
    ucher
    -0.15
    seg
    -0.15
     sort
    -0.15
     kind
    -0.14
    afs
    -0.14
    ask
    -0.14
    macros
    -0.13
    elf
    -0.13
    POSITIVE LOGITS
     operation
    0.25
    operation
    0.21
     effort
    0.18
     action
    0.18
    illes
    0.17
     activity
    0.17
     coverage
    0.17
     expression
    0.17
     operations
    0.17
     affairs
    0.17
    Act Density 0.241%

    No Known Activations