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

    Neuronpedia

    INDEX
    Explanations

    instances of pointing or indicating actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.45
    UserDTO
    -0.43
    Життєпис
    -0.42
    -0.39
     démoc
    -0.39
    yarnpkg
    -0.38
     quæ
    -0.38
    Становништво
    -0.37
    Nyc
    -0.37
     creativo
    -0.36
    POSITIVE LOGITS
     pointing
    0.81
     pointed
    0.77
     apont
    0.63
    pointed
    0.62
    pointing
    0.61
     aimed
    0.59
     estekak
    0.58
     aiming
    0.58
     directed
    0.54
    Toward
    0.52
    Act Density 0.099%

    No Known Activations