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

    Neuronpedia

    INDEX
    Explanations

    phrases related to new beginnings or changes across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     backgrounds
    -0.17
     dint
    -0.15
    rng
    -0.15
    743
    -0.14
    Ïħν
    -0.14
    amage
    -0.14
     background
    -0.14
     latest
    -0.14
    uki
    -0.13
    ToPoint
    -0.13
    POSITIVE LOGITS
     breed
    0.31
     era
    0.30
     Breed
    0.23
     Era
    0.21
     wave
    0.21
    era
    0.21
    -era
    0.21
     reality
    0.20
     normal
    0.20
     normals
    0.20
    Act Density 0.097%

    No Known Activations