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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "can" and its variations related to possibility or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ically
    -0.16
    irror
    -0.16
    ought
    -0.16
    ialect
    -0.15
    iously
    -0.15
    atively
    -0.15
     themselves
    -0.14
    èm
    -0.14
    amt
    -0.14
     itself
    -0.14
    POSITIVE LOGITS
     expect
    0.25
     always
    0.24
    expect
    0.22
    always
    0.20
     bet
    0.20
     either
    0.20
     Always
    0.19
    Expect
    0.19
     Expect
    0.19
     certainly
    0.18
    Act Density 0.148%

    No Known Activations