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

    Neuronpedia

    INDEX
    Explanations

    legal terms related to criminal charges and guilty pleas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Gratis
    -0.16
    lund
    -0.15
    aylight
    -0.15
    aines
    -0.15
    oller
    -0.15
    _hdl
    -0.14
    rouw
    -0.14
    ActionCreators
    -0.14
    nore
    -0.14
    nett
    -0.14
    POSITIVE LOGITS
     counts
    0.27
     Counts
    0.24
     attempted
    0.23
    counts
    0.21
     Attempt
    0.21
     veh
    0.21
     sod
    0.20
     Count
    0.20
    Counts
    0.20
     count
    0.19
    Act Density 0.028%

    No Known Activations