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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating agreement or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ‘
    -0.82
     autorytatywna
    -0.80
     “
    -0.76
     Berge
    -0.75
     useNavigate
    -0.71
    муля
    -0.66
     bir
    -0.66
    bitat
    -0.65
     Wheeler
    -0.64
    devtool
    -0.63
    POSITIVE LOGITS
     OK
    1.42
     ok
    1.25
    팎
    1.24
     Ok
    1.23
     okay
    1.21
     alright
    1.20
    OK
    1.19
    Ok
    1.19
     OKAY
    1.14
    OKAY
    1.14
    Act Density 0.038%

    No Known Activations