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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PureComponent
    -0.17
    uet
    -0.16
    jit
    -0.15
     berg
    -0.14
    irk
    -0.14
    opia
    -0.14
     Gra
    -0.14
     backstage
    -0.14
    uke
    -0.14
    iag
    -0.14
    POSITIVE LOGITS
     floor
    1.04
    floor
    0.90
     Floor
    0.90
     floors
    0.84
    Floor
    0.82
    -floor
    0.81
    _floor
    0.74
     Floors
    0.69
    .floor
    0.65
     ceiling
    0.65
    Act Density 0.143%

    No Known Activations