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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ask
    -0.15
    iness
    -0.14
    eed
    -0.14
    itol
    -0.14
     eject
    -0.14
    nah
    -0.14
    adox
    -0.14
     lúc
    -0.13
    eya
    -0.13
    istance
    -0.13
    POSITIVE LOGITS
    741
    0.14
     Birch
    0.14
    ipl
    0.14
    opak
    0.14
    esson
    0.14
    535
    0.13
    643
    0.13
    太éĥİ
    0.13
    intendent
    0.13
    541
    0.13
    Act Density 0.094%

    No Known Activations