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

    Neuronpedia

    INDEX
    Explanations

    themes of loss, abandonment, and failure

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

    lost, missing, or abandoned things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    izarse
    -0.41
     Sünde
    -0.39
    исленность
    -0.38
     aanwezig
    -0.37
     Paglinawan
    -0.36
    miljø
    -0.36
     výbě
    -0.36
     Träger
    -0.35
     kepad
    -0.35
     käyttö
    -0.35
    POSITIVE LOGITS
    AnchorStyles
    0.58
     laptop
    0.57
    istoitu
    0.55
     glory
    0.54
     livestock
    0.54
     rubber
    0.52
     lithium
    0.52
    innoc
    0.51
    MLLoader
    0.51
     يتيمه
    0.51
    Act Density 0.077%

    No Known Activations