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

    Neuronpedia

    INDEX
    Explanations

    names of authors

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, possibly authors or contributors, along with their associated works or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VALUE
    -0.64
    Magikarp
    -0.62
    canon
    -0.61
    Battery
    -0.61
    essential
    -0.59
    Ĥİ
    -0.58
    coded
    -0.58
     Expo
    -0.58
    FactoryReloaded
    -0.57
     chanted
    -0.57
    POSITIVE LOGITS
    .,
    1.08
     et
    1.01
    .;
    0.87
    .:
    0.81
     Jr
    0.78
    .-
    0.75
     Functional
    0.74
     Handbook
    0.74
     Dept
    0.73
     Identification
    0.73
    Act Density 0.103%

    No Known Activations