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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the concept of innovation or something being new

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    new followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.63
     שוליים
    -0.60
    sizeCache
    -0.57
    SourceChecksum
    -0.57
    makeConstraints
    -0.56
    findpost
    -0.55
     resourceCulture
    -0.53
    𝟹
    -0.53
    ApiModelProperty
    -0.52
    पया
    -0.52
    POSITIVE LOGITS
    ſelves
    0.67
     poffible
    0.64
     ſeveral
    0.61
     ſch
    0.54
    ſelf
    0.53
     ſta
    0.52
     ſmall
    0.52
     Diſ
    0.51
     themſelves
    0.51
     myſelf
    0.51
    Act Density 0.019%

    No Known Activations