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

    Neuronpedia

    INDEX
    Explanations

    action-oriented phrases related to evaluations and processes

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

    develop, purchase, research, determine, invest, review, configure, post

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.64
    #
    -0.56
    posedge
    -0.52
    WriteBarrier
    -0.46
    AndEndTag
    -0.44
     ur
    -0.44
    évaluateur
    -0.43
     ela
    -0.42
    ElementException
    -0.42
    avigation
    -0.42
    POSITIVE LOGITS
     themſelves
    0.59
     zijne
    0.55
    ſelf
    0.48
     ſtre
    0.47
     Italijani
    0.47
     ſta
    0.47
     ciasc
    0.47
     quæ
    0.47
    leſs
    0.47
    ſelves
    0.46
    Act Density 0.173%

    No Known Activations