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

    Neuronpedia

    INDEX
    Explanations

    instances where an action is being initiated or started

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "initiate" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rust
    -0.74
    equality
    -0.72
    iverse
    -0.71
     Stain
    -0.69
     crunch
    -0.68
    dain
    -0.67
    yll
    -0.67
    UFF
    -0.66
    Rust
    -0.65
    adata
    -0.65
    POSITIVE LOGITS
     initiate
    3.13
     initiated
    3.00
     initi
    2.95
     initiation
    2.71
     initiating
    2.52
     Initi
    2.12
     Init
    1.36
     commenced
    1.29
     commence
    1.23
     instituted
    1.13
    Act Density 0.018%

    No Known Activations