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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to control parameters or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ddelweddau
    -0.69
    ьаж
    -0.67
     thức
    -0.49
    Демографія
    -0.49
    Mag
    -0.48
     Castig
    -0.47
    ilera
    -0.46
     TMZ
    -0.46
    medskip
    -0.46
     Biôgrafia
    -0.45
    POSITIVE LOGITS
    0.73
    0.58
    rrggbb
    0.57
    +:+
    0.55
    Device
    0.53
     Mum
    0.53
    Mum
    0.51
    geometric
    0.49
    ńcz
    0.48
    ArgsConstructor
    0.47
    Act Density 0.151%

    No Known Activations